INDEX
Explanations
mentions of film or filmmaking
New Auto-Interp
Negative Logits
anwhile
-0.78
lain
-0.70
compr
-0.69
WARN
-0.65
convict
-0.65
è¦ļéĨĴ
-0.64
compounded
-0.62
Reborn
-0.61
Universities
-0.60
Predict
-0.60
POSITIVE LOGITS
ters
1.37
tered
1.26
igree
1.20
thy
1.15
tering
1.14
ming
1.05
teness
0.96
inary
0.92
cipled
0.92
ename
0.91
Activations Density 0.004%