INDEX
Explanations
mentions of comic books
New Auto-Interp
Negative Logits
ntil
-0.92
achev
-0.74
lain
-0.73
tu
-0.72
attled
-0.71
aye
-0.71
loo
-0.70
ĪĴ
-0.70
animous
-0.70
hid
-0.68
POSITIVE LOGITS
Comics
1.03
relief
0.88
strip
0.87
book
0.85
sans
0.84
strip
0.82
ograp
0.79
Sans
0.78
books
0.77
adaptation
0.77
Activations Density 0.072%