The Intuition of Recurrent Neural Networks

This is an introductory article. I suggest you know the works behind gradient descent, some linear algebra, and basic DL knowledge . There is a magic in recurrent neural networks that I have always cherished. Within a few dozen minutes of training his model (with rather arbitrarily-chosen hyperparameters), it started to generate meaning that was on the edge of making sense. How is it possible to extract the essence of previous terms to guess future words?