INDEX
Explanations
proper nouns, particularly related to filmmakers and movies
references to Quentin Tarantino and his films
New Auto-Interp
Negative Logits
DOM
-0.70
HCR
-0.69
CHR
-0.66
GY
-0.64
WAYS
-0.63
clipboard
-0.63
Gamergate
-0.62
Article
-0.62
PT
-0.61
åĮ
-0.61
POSITIVE LOGITS
Tarant
1.53
ulas
1.05
illo
0.99
arella
0.93
illas
0.91
itone
0.88
ino
0.88
rent
0.87
arium
0.81
ula
0.80
Activations Density 0.013%