What is the explanation of discretized log logistic in the following code? Is there any reference regarding this piece of code?

Question

I have taken the following piece of code from the OpenAI code of GitHub from the following link:

https://github.com/openai/iaf/blob/master/tf_utils/distributions.py#L28

def discretized_logistic(mean, logscale, binsize=1 / 256.0, sample=None):
      scale = tf.exp(logscale)
      sample = (tf.floor(sample / binsize) * binsize - mean) / scale
      logp = tf.log(tf.sigmoid(sample + binsize / scale) - tf.sigmoid(sample) + 1e-7)
      return tf.reduce_sum(logp, [1, 2, 3])

I am unable to understand mathematical intuition or explanation of the above code. Even, I am unable to find the reference for this. Could you please explain?