INDEX
Explanations
references to comic books
references to comic books
New Auto-Interp
Negative Logits
ntil
-0.97
sembly
-0.82
loo
-0.81
rake
-0.80
doors
-0.77
tu
-0.77
achev
-0.76
undai
-0.76
yip
-0.74
ĪĴ
-0.74
POSITIVE LOGITS
Comics
0.90
strip
0.89
relief
0.86
comic
0.84
book
0.82
comics
0.80
illust
0.79
shorts
0.78
adaptation
0.77
strips
0.76
Activations Density 0.017%