These things are still strange to everyone. The fact matrixes of numbers can seemingly conceptualize almost anything is just freaking weird.

Of course there may be an electronic civilization out there that would say the same things about our mushy brains... "They are made out of meat!"

In principle a large enough neural network can provably approximate any continuous function. Since arithmetic can be represented with a concrete grammar, it's not surprising to me that an LLM could contain an abstract representation if trained correctly.