INDEX
Explanations
themes related to character choices and challenges in movies
New Auto-Interp
Negative Logits
Mickey
-0.17
.external
-0.16
auer
-0.16
spiders
-0.15
odian
-0.15
ghosts
-0.15
orpion
-0.15
erli
-0.14
.tm
-0.14
mlink
-0.14
POSITIVE LOGITS
Ú¯ÙĪ
0.17
(vo
0.16
hone
0.15
erk
0.15
tero
0.14
gross
0.14
endra
0.14
Fletcher
0.14
Illum
0.14
èĽĭ
0.14
Activations Density 0.039%