Update README.md

README.md

@@ -22,4 +22,6 @@ tokenizer.decode([10163, 46387])  # '<unused123> pigeon'
 gpt2_tokenizer.decode([10163, 46387])  # '123 pigeon'
 ```
 
-[PaLM](https://arxiv.org/abs/2204.02311) does this.
+- This is for my investigations into the arithmetic capabilities of large language models.
+- [PaLM](https://arxiv.org/abs/2204.02311) does this.
+- Many models (illustriously, [GPT-3](https://arxiv.org/abs/2005.14165)) use the GPT-2 tokenizer, which doesn't do this.