ChatGPT doesn’t always exhibit anomalous behavoir for the token DragonMagazine:
Although it still sometimes does:
Quotation marks appear to affect whether it handles the string correctly:
This is because of tokenization. Tutorial about BPE (which OpenAI use) is here. Specifically in this case:
ChatGPT doesn’t always exhibit anomalous behavoir for the token DragonMagazine:
Although it still sometimes does:
Quotation marks appear to affect whether it handles the string correctly:
This is because of tokenization. Tutorial about BPE (which OpenAI use) is here. Specifically in this case: