Because the phenomenon happens at the tokenization level, GPT at runtime can’t, like, “perceive” the letters. It has no idea that “SolidGoldMagikarp” looks similar to “SolidSoldMagikarp” (or the reverse)
Because the phenomenon happens at the tokenization level, GPT at runtime can’t, like, “perceive” the letters. It has no idea that “SolidGoldMagikarp” looks similar to “SolidSoldMagikarp” (or the reverse)