# Correct input-output relationship for binary logistic regression

In section 6.2.2.2 Sigmoid Units for Bernoulli Output Distributions of the Deep Learning book, the author gave a logistic regression model for binary classification $P(y)=\sigma(z)$ where $\sigma$ is the logistic sigmoid function and $z$ is a linear/affine transformation of input $x$. The author then said that:

Saturation thus occurs only when the model already has the right answer—when $y=1$ and $z$ is very positive, or $y=0$ and $z$ is very negative.

I'm just wondering why this is the correct input-output relationship to be learned.