INDEX
Explanations
references to comics and comic books
New Auto-Interp
Negative Logits
al
-0.18
yr
-0.17
comed
-0.16
eut
-0.16
udit
-0.16
abor
-0.15
essor
-0.15
ACLE
-0.14
ie
-0.14
ecom
-0.14
POSITIVE LOGITS
Relief
0.28
strip
0.28
-strip
0.27
-book
0.26
relief
0.26
book
0.25
Strip
0.24
lopedia
0.23
book
0.23
strips
0.22
Activations Density 0.007%