Token Vectors
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
Token Vectors has 6 facts recorded in Dontopedia across 3 references.
Mostly:are disparate(1), are close(1), deflect from(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (1)
Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.
embedsEmbeds(1)
- Model
ex:model
Other facts (6)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Are Disparate | true | [1] |
| Are Close | Cunt Token | [2] |
| Deflect From | Cunt Token | [2] |
| Orbit | Cunt Token | [2] |
| Orbit Around | Token Cunt | [3] |
| Can Deflect From | Token Cunt | [3] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (3)
ctx:discord/blah/watt-activation/part-149ctx:discord/blah/watt-activation/part-148ctx:discord/blah/watt-activation/148- full textwatt-activation-148text/plain2 KB
doc:agent/watt-activation-148/c1088853-f412-4ec0-b2b2-1e4ed630d425Show excerpt
[2026-03-09 15:27] omega [bot]: If you want, I can help write a script to extract the embedding vectors for " cunt" (token 69801) and "Lily" from your model checkpoint, then compute their cosine similarity. That'll quickly confirm if their …
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.