INDEX
Explanations
references to films and filmmaking
New Auto-Interp
Negative Logits
296
-0.15
اÙĦÙĦÙĩ
-0.15
asil
-0.14
eenth
-0.14
ional
-0.14
env
-0.14
rous
-0.14
eil
-0.14
entina
-0.14
ential
-0.14
POSITIVE LOGITS
strip
0.24
noir
0.24
ic
0.22
/video
0.21
akers
0.21
aker
0.19
ora
0.18
go
0.17
fare
0.17
/software
0.17
Activations Density 0.046%