Ars provides this asterisk:

Even though the spreadsheet contains a complete AI language model, you can’t chat with it like ChatGPT. Instead, users input words in other cells and see the predictive results displayed in different cells almost instantly. … [L]anguage models like GPT-2 were designed to do next-token prediction, which means they try to complete an input (called a prompt, which is encoded into chunks called tokens) with the most likely text. The prediction could be the continuation of a sentence or any other text-based task, such as software code. Different sheets in Anand’s Excel file allow users to get a sense of what is going on under the hood while these predictions are taking place.

Direct github link here; YouTube intro from the creator here.