What's interesting is that I can ask ChatGPT to create a table with the substring of the last three letters of each word, and put it into a new column (this operation by itself is amazing in and of itself, with correct format). It still gets the substring wrong for "lunar" but gets it correct for a bunch of other words. It must think that lunar gets tokenized to "lar" for some reason. I have figured out a way to get around that, but if I tell it that last 3 letters of "lunar" are "nar" it will correct itself and regenerate my table with the correction.

So mind blowing.