INDEX
Explanations
mentions of comic books
mentions of comic books and comic book-related terms
New Auto-Interp
Negative Logits
ntil
-0.86
attled
-0.73
edIn
-0.72
tu
-0.70
rake
-0.70
aye
-0.68
lain
-0.67
achev
-0.67
doors
-0.66
ldon
-0.66
POSITIVE LOGITS
relief
0.95
book
0.94
Comics
0.92
strip
0.89
sans
0.86
strip
0.83
book
0.81
books
0.81
ograp
0.79
Sans
0.77
Activations Density 0.028%