INDEX
Explanations
occurrences of specific character names or creators associated with comic book adaptations
New Auto-Interp
Negative Logits
paced
-0.69
compliments
-0.67
EngineDebug
-0.66
Unic
-0.65
chall
-0.64
Grid
-0.62
compliment
-0.62
TOUR
-0.58
Jagu
-0.58
reclaimed
-0.57
POSITIVE LOGITS
ages
0.69
oka
0.66
lest
0.66
ould
0.66
imp
0.64
owell
0.61
ol
0.61
OV
0.60
imer
0.59
Near
0.58
Activations Density 0.038%