LLMs operate at token level, not word. it doesn't operate in terms of "traumatic", "over-training", "over" or "training", but rather "tr" "aum" "at" "ic, ", etc.
king and rex (king in latin) map to different tokens but will map to very similar vectors.
And "毛片免费观看" (Free porn movies), "天天中彩票能" (Win the lottery every day), "热这里只有精品" (Hot, only fine products here) etc[1].
Some LLMs can output nerd font glyphs and others can't.
If I recall grok code fast can but codex and sonnet can't