Illustration 1 of 3

From Words to Numbers

People love to say an LLM is "just fancy autocorrect." Watch what really happens to a single word — bank — and you'll see it's something else entirely.

{{ captionTitle }}

{{ captionBody }}

Long or rare words get split too. “deposit” might become de + posit, and “librarian” → librari + an. The model always works in these pieces — that's all a token is.

Why this isn't autocorrect

Autocorrect guesses the next word from raw frequency — every “bank” looks the same to it. Attention does the opposite: it lets the sentence change what a word means. That single idea is what turns a list of numbers into understanding.

See the space these words live in
The sentences
“the river bank”
{{ a.label }}
“the bank deposit”
{{ a.label }}
The vector behind “bank” {{ vecBadge }}
river bank
bank deposit
The space of meaning
water & nature
money & finance
{{ r.label }}
bank
bank