INDEX
Explanations
references to award ceremonies and accolades in the film industry
New Auto-Interp
Negative Logits
olson
-0.16
çĻ
-0.16
ipur
-0.15
nick
-0.15
Mour
-0.15
arters
-0.15
cum
-0.14
punk
-0.14
tach
-0.14
ÑĢÑĸв
-0.14
POSITIVE LOGITS
Globe
0.41
Glob
0.40
glob
0.31
globe
0.30
Raspberry
0.27
Satellite
0.26
.glob
0.24
Tomato
0.24
glob
0.23
_glob
0.22
Activations Density 0.005%