INDEX
Explanations
names related to the color gray or variations of it
mentions of specific Pokémon species
New Auto-Interp
Negative Logits
urity
-0.77
========
-0.77
uador
-0.72
elligent
-0.72
ivity
-0.70
itudes
-0.70
abulary
-0.69
itude
-0.68
uple
-0.66
certific
-0.66
POSITIVE LOGITS
hound
1.41
beard
1.02
hawk
1.01
Matter
0.94
haired
0.90
wolf
0.89
naire
0.87
hill
0.86
Goo
0.86
bear
0.86
Activations Density 0.032%