INDEX
Explanations
the word "Hulk" and variations of it in the text
mentions of the character 'Hulk'
New Auto-Interp
Negative Logits
Continued
-0.71
İĭ
-0.68
Candle
-0.67
Danger
-0.65
®
-0.64
Kyoto
-0.64
delicate
-0.62
Granted
-0.62
cale
-0.62
cropped
-0.61
POSITIVE LOGITS
ulk
1.60
ulkan
0.93
inous
0.88
anova
0.87
okane
0.84
owl
0.82
urus
0.82
aroo
0.82
ul
0.80
rats
0.80
Activations Density 0.007%