INDEX
Explanations
references to comic conventions and comic-related content
New Auto-Interp
Negative Logits
lain
-0.85
attled
-0.84
¿½
-0.82
ntil
-0.80
aye
-0.80
ngth
-0.79
uckland
-0.77
etheless
-0.75
mathemat
-0.73
loo
-0.73
POSITIVE LOGITS
Relief
0.99
Comics
0.97
Expo
0.96
Sans
0.94
ograp
0.89
Comic
0.87
osity
0.83
Shop
0.82
Artists
0.82
afort
0.80
Activations Density 0.006%