INDEX
Explanations
references to comic books
references to comic books and their related content
New Auto-Interp
Negative Logits
ntil
-0.81
lain
-0.77
edIn
-0.76
aband
-0.72
tu
-0.70
ngth
-0.70
aye
-0.69
WARD
-0.69
ITNESS
-0.69
uckland
-0.68
POSITIVE LOGITS
relief
1.01
book
0.99
book
0.94
strip
0.91
ograp
0.91
sans
0.89
Sans
0.85
strip
0.85
Comics
0.85
strips
0.83
Activations Density 0.038%