INDEX
Explanations
references to movies and cinematic works
New Auto-Interp
Negative Logits
_movie
-0.25
movies
-0.22
Movies
-0.22
Movie
-0.22
Movies
-0.20
Movie
-0.20
movie
-0.20
ively
-0.18
ç͵影
-0.17
_movies
-0.17
POSITIVE LOGITS
go
0.29
going
0.24
clip
0.24
/show
0.22
buff
0.22
guide
0.21
industry
0.20
/book
0.20
buff
0.20
gue
0.20
Activations Density 0.031%