INDEX
Explanations
details related to movie production, film culture, and the film industry
New Auto-Interp
Negative Logits
ciating
-0.74
attled
-0.73
ilities
-0.71
RESULTS
-0.67
lies
-0.65
arity
-0.64
hee
-0.63
tnc
-0.63
urion
-0.62
rian
-0.62
POSITIVE LOGITS
studios
1.13
studio
1.06
Film
1.03
ovies
1.03
goers
1.02
theaters
1.01
theater
0.97
film
0.96
films
0.94
theat
0.94
Activations Density 1.817%