INDEX
Explanations
references to Hollywood, particularly in the context of movies and actors
mentions and references to Hollywood and its films
New Auto-Interp
Negative Logits
Razer
-0.74
Lew
-0.67
WIN
-0.66
Roland
-0.65
Murd
-0.64
Ob
-0.64
Myst
-0.64
Coul
-0.63
Conway
-0.63
Warden
-0.63
POSITIVE LOGITS
ollywood
0.97
jriwal
0.92
ulhu
0.88
India
0.86
fare
0.83
oji
0.82
ãħĭ
0.77
eele
0.77
gi
0.77
Asia
0.76
Activations Density 0.016%