It's something of the law of averages. At their core, an LLM is a sophisticated text prediction algorithm, that boils down the entire corpus of human language into numeric tokens, that it averages out, and creates entire sentences by determining the next most likely word to fill the space.
Given enough data, and you need a tremendous amount of it for an LLM, patterns start to come about, and many of those end up the ones that we see in LLMs.
Reminds me of the bread jesus incident.