Hacker News Reader

The trained embedding vectors for the token equivalents of W4 and W-4 would be mapped to a similar space due to their appearance in the same contexts.

View on HN

The point of the GP post is that the "w-4" token had very different results from ["w", "-4"] or similar algorithms where the "w" and "4" wound up in separate tokens.

Reply on news.ycombinator.com