diff --git a/GPy/models/warped_gp.py b/GPy/models/warped_gp.py
index d35c1a15..419a4104 100644
--- a/GPy/models/warped_gp.py
+++ b/GPy/models/warped_gp.py
@@ -68,22 +68,22 @@ class WarpedGP(GP):
         arg2 = np.ones(shape=gh_samples.shape).dot(mean.T)
         return self.warping_function.f_inv(arg1 + arg2, y=pred_init)
 
-    def _get_warped_mean(self, mean, std, pred_init=None, deg_gauss_hermite=100):
+    def _get_warped_mean(self, mean, std, pred_init=None, deg_gauss_hermite=20):
         """
         Calculate the warped mean by using Gauss-Hermite quadrature.
         """
         gh_samples, gh_weights = np.polynomial.hermite.hermgauss(deg_gauss_hermite)
-        gh_samples = gh_samples[:,None]
-        gh_weights = gh_weights[None,:]
+        gh_samples = gh_samples[:, None]
+        gh_weights = gh_weights[None, :]
         return gh_weights.dot(self._get_warped_term(mean, std, gh_samples)) / np.sqrt(np.pi)
 
-    def _get_warped_variance(self, mean, std, pred_init=None, deg_gauss_hermite=100):
+    def _get_warped_variance(self, mean, std, pred_init=None, deg_gauss_hermite=20):
         """
         Calculate the warped variance by using Gauss-Hermite quadrature.
         """
         gh_samples, gh_weights = np.polynomial.hermite.hermgauss(deg_gauss_hermite)
-        gh_samples = gh_samples[:,None]
-        gh_weights = gh_weights[None,:]
+        gh_samples = gh_samples[:, None]
+        gh_weights = gh_weights[None, :]
         arg1 = gh_weights.dot(self._get_warped_term(mean, std, gh_samples, 
                                                     pred_init=pred_init) ** 2) / np.sqrt(np.pi)
         arg2 = self._get_warped_mean(mean, std, pred_init=pred_init,
@@ -91,7 +91,7 @@ class WarpedGP(GP):
         return arg1 - (arg2 ** 2)
 
     def predict(self, Xnew, which_parts='all', pred_init=None, full_cov=False, Y_metadata=None,
-                median=False, deg_gauss_hermite=100, likelihood=None):
+                median=False, deg_gauss_hermite=20, likelihood=None):
         """
         Prediction results depend on:
         - The value of the self.predict_in_warped_space flag
diff --git a/GPy/testing/model_tests.py b/GPy/testing/model_tests.py
index 4b9d11ee..2b9add02 100644
--- a/GPy/testing/model_tests.py
+++ b/GPy/testing/model_tests.py
@@ -307,6 +307,31 @@ class MiscTests(unittest.TestCase):
  
         np.testing.assert_almost_equal(preds, warp_preds)
 
+    def test_warped_gp_log(self):
+        """
+        A WarpedGP with the log warping function should be
+        equal to a standard GP with log labels.
+        """
+        k = GPy.kern.RBF(1)
+        Y = np.abs(self.Y)
+        logY = np.log(Y)
+        m = GPy.models.GPRegression(self.X, logY, kernel=k)
+        #m.optimize()
+        m['Gaussian_noise.variance'] = 1e-4
+        preds = m.predict(self.X)[0]
+
+        warp_k = GPy.kern.RBF(1)
+        warp_f = GPy.util.warping_functions.LogFunction()
+        warp_m = GPy.models.WarpedGP(self.X, Y, kernel=warp_k, warping_function=warp_f)
+        warp_m.optimize()
+        warp_m['.*'] = 1.0
+        warp_m['Gaussian_noise.variance'] = 1e-4
+        warp_preds = warp_m.predict(self.X, median=True)[0]
+        #print np.exp(preds)
+        #print warp_preds
+ 
+        np.testing.assert_almost_equal(np.exp(preds), warp_preds)
+
     #@unittest.skip('Comment this to plot the modified sine function')
     def test_warped_gp_sine(self):
         """
@@ -316,12 +341,13 @@ class MiscTests(unittest.TestCase):
         X = (2 * np.pi) * np.random.random(151) - np.pi
         Y = np.sin(X) + np.random.normal(0,0.2,151)
         Y = np.array([np.power(abs(y),float(1)/3) * (1,-1)[y<0] for y in Y])
-        Y = np.abs(Y)
+        #Y = np.abs(Y)
         
         import matplotlib.pyplot as plt
         warp_k = GPy.kern.RBF(1)
-        #warp_f = GPy.util.warping_functions.TanhFunction(n_terms=2)
-        warp_f = GPy.util.warping_functions.LogisticFunction(n_terms=2)
+        warp_f = GPy.util.warping_functions.TanhFunction(n_terms=2)
+        #warp_f = GPy.util.warping_functions.LogisticFunction(n_terms=2)
+        #warp_f = GPy.util.warping_functions.LogitFunction(n_terms=1)
         warp_m = GPy.models.WarpedGP(X[:, None], Y[:, None], kernel=warp_k, warping_function=warp_f)
 
         m = GPy.models.GPRegression(X[:, None], Y[:, None])
diff --git a/GPy/util/warping_functions.py b/GPy/util/warping_functions.py
index c62ed08e..548877e5 100644
--- a/GPy/util/warping_functions.py
+++ b/GPy/util/warping_functions.py
@@ -70,6 +70,7 @@ class TanhFunction(WarpingFunction):
         self.link_parameter(self.psi)
         self.link_parameter(self.d)
         self.initial_y = initial_y
+        self.rate = 0.1
 
     def f(self, y):
         """
@@ -94,28 +95,19 @@ class TanhFunction(WarpingFunction):
         """
 
         z = z.copy()
-        
-        if y is None:
-            # The idea here is to initialize y with +1 where
-            # z is positive and -1 where it is negative.
-            # For negative z, Newton-Raphson diverges 
-            # if we initialize y with a positive value (and vice-versa).
-            y = ((z > 0) * 1.) - (z <= 0)
-            if self.initial_y is not None:
-                y *= self.initial_y
+        y = np.ones_like(z)
 
         it = 0
         update = np.inf
-
-        while it == 0 or (np.abs(update).sum() > 1e-10 and it < max_iterations):
+        while np.abs(update).sum() > 1e-10 and it < max_iterations:
             fy = self.f(y)
             fgrady = self.fgrad_y(y)
             update = (fy - z) / fgrady
-            y -= update
+            y -= self.rate * update
             it += 1
         if it == max_iterations:
             print("WARNING!!! Maximum number of iterations reached in f_inv ")
-            print("Sum of updates: %.4f" % np.sum(update))
+            print("Sum of roots: %.4f" % np.sum(fy - z))
         return y
 
     def fgrad_y(self, y, return_precalc=False):
@@ -391,3 +383,135 @@ class LogisticFunction(WarpingFunction):
         self.psi.gradient[:] = warping_grads[:, :-1]
         self.d.gradient[:] = warping_grads[0, -1]
 
+
+class LogitFunction(WarpingFunction):
+    """
+    A sum of logit functions.
+    """
+    def __init__(self, n_terms=1, initial_y=None):
+        """
+        n_terms specifies the number of logistic terms to be used
+        """
+        self.n_terms = n_terms
+        self.num_parameters = 3 * self.n_terms
+        self.psi = np.ones((self.n_terms, 3))
+        super(LogitFunction, self).__init__(name='warp_logit')
+        self.psi = Param('psi', self.psi)
+        self.psi[:, :2].constrain_positive()
+        self.link_parameter(self.psi)
+        self.initial_y = initial_y
+        self.e = 1e-5
+
+    def _logit(self, y):
+        a, b, c = self.psi[0]
+        y += self.e
+        return ((np.log(y) - np.log(a - y)) / b) + c
+
+    def f(self, y):
+        """
+        Transform y with f using parameter vector psi
+        psi = [[a,b,c]]
+
+        :math:`f = (y * d) + \\sum_{terms} a * logistic(b *(y + c))`
+        """
+        z = np.zeros_like(y)
+        for i in xrange(self.n_terms):
+            a, b, c = self.psi[i]
+            z += self._logit(y)
+        return z
+
+    def f_inv(self, z, max_iterations=100, y=None):
+        """
+        calculate the numerical inverse of f
+
+        :param max_iterations: maximum number of N.R. iterations
+        """
+        z = z.copy()
+        if y is None:
+            # The idea here is to initialize y with +1 where
+            # z is positive and -1 where it is negative.
+            # For negative z, Newton-Raphson diverges 
+            # if we initialize y with a positive value (and vice-versa).
+            y = ((z > 0) * 1.) - (z <= 0)
+            if self.initial_y is not None:
+                y *= self.initial_y
+        it = 0
+        update = np.inf
+        while it == 0 or (np.abs(update).sum() > 1e-10 and it < max_iterations):
+            fy = self.f(y)
+            fgrady = self.fgrad_y(y)
+            update = (fy - z) / fgrady
+            y -= update
+            it += 1
+        if it == max_iterations:
+            print("WARNING!!! Maximum number of iterations reached in f_inv ")
+            print("Sum of updates: %.4f" % np.sum(update))
+        return y
+
+    def fgrad_y(self, y, return_precalc=False):
+        """
+        Gradient of f w.r.t to y ([N x 1])
+        This vectorized version calculates all summation terms
+        at the same time (since the grad of a sum is the sum of the grads).
+
+        :returns: Nx1 vector of derivatives, unless return_precalc is true, 
+        then it also returns the precomputed stuff
+        """
+        a, b, c = self.psi[0]
+
+        # vectorized version
+        # term = b * (y + c)
+        y += self.e
+        yb = y * b
+        ab = a * b
+        grad = (1. / yb) + (1. / (ab - yb))
+
+        if return_precalc:
+            return grad, yb, ab
+        return grad
+
+    def fgrad_y_psi(self, y, return_covar_chain=False):
+        """
+        gradient of f w.r.t to y and psi
+
+        :returns: NxIx4 tensor of partial derivatives
+        """
+        grad, yb, ab = self.fgrad_y(y, return_precalc=True)
+        gradients = np.zeros((y.shape[0], y.shape[1], self.n_terms, 3))
+        for i in xrange(self.n_terms):
+            a, b, c  = self.psi[i]
+            gradients[:, :, i, 0] = -b / ((ab - yb) ** 2)
+            yb2 = y * (b ** 2)
+            ab2 = a * (b ** 2)
+            gradients[:, :, i, 1] = - (1. / yb2) - (1. / (ab2 - yb2))
+            #gradients[:, :, i, 2] = 0.0
+
+        if return_covar_chain:
+            covar_grad_chain = np.zeros((y.shape[0], y.shape[1], self.n_terms, 3))
+            for i in xrange(self.n_terms):
+                a, b, c = self.psi[i]
+                covar_grad_chain[:, :, i, 0] = - (1. / (ab - yb))
+                covar_grad_chain[:, :, i, 1] = - (np.log(y) - np.log(a - y)) / (b ** 2)
+                covar_grad_chain[:, :, i, 2] = 1.0
+            return gradients, covar_grad_chain
+
+        return gradients
+
+    def _get_param_names(self):
+        variables = ['a', 'b', 'c']
+        names = sum([['warp_logit_%s_t%i' % (variables[n],q) for n in range(3)] 
+                     for q in range(self.n_terms)],[])
+        names.append('warp_logit')
+        return names
+
+    def update_grads(self, Y_untransformed, Kiy):
+        grad_y = self.fgrad_y(Y_untransformed)
+        grad_y_psi, grad_psi = self.fgrad_y_psi(Y_untransformed,
+                                                return_covar_chain=True)
+        djac_dpsi = ((1.0 / grad_y[:, :, None, None]) * grad_y_psi).sum(axis=0).sum(axis=0)
+        dquad_dpsi = (Kiy[:, None, None, None] * grad_psi).sum(axis=0).sum(axis=0)
+
+        warping_grads = -dquad_dpsi + djac_dpsi
+
+        self.psi.gradient[:] = warping_grads[:, :]
+