INDEX
Explanations
specific genres and themes related to movies and television shows
New Auto-Interp
Negative Logits
uh
-0.17
itters
-0.16
.sax
-0.14
eras
-0.14
.locale
-0.14
Åĵ
-0.14
cies
-0.13
Technique
-0.13
aws
-0.13
em
-0.13
POSITIVE LOGITS
-themed
0.25
themed
0.22
theme
0.20
-theme
0.19
themes
0.19
theme
0.18
ç¯
0.16
scenes
0.15
motif
0.15
THEME
0.15
Activations Density 0.247%