INDEX
Explanations
mentions of the name "Cain" and related characters
New Auto-Interp
Negative Logits
uyomi
-0.76
DragonMagazine
-0.72
ODUCT
-0.71
awaru
-0.71
plom
-0.70
ogyn
-0.69
natureconservancy
-0.68
oppable
-0.66
iculty
-0.66
essert
-0.65
POSITIVE LOGITS
Cain
0.94
ous
0.94
son
0.80
zilla
0.80
bolt
0.79
omics
0.77
cia
0.75
hurst
0.74
Vel
0.72
aire
0.70
Activations Density 0.010%