INDEX
Explanations
titles or references to popular culture, movies, games, and iconic characters
references to film series, characters, or elements from cinematic universes
New Auto-Interp
Negative Logits
govtrack
-0.75
endum
-0.69
Statement
-0.69
erity
-0.68
iasis
-0.68
Response
-0.68
eat
-0.67
Gov
-0.67
INST
-0.67
lication
-0.66
POSITIVE LOGITS
genre
1.42
franchise
1.34
franchises
1.24
comics
1.20
superhero
1.19
universes
1.19
characters
1.16
mythology
1.15
universe
1.15
trilogy
1.15
Activations Density 0.322%