INDEX
Explanations
objects and tools related to cooking and weapons
New Auto-Interp
Negative Logits
הערות
-0.70
seamnă
-0.56
cosplay
-0.56
demografica
-0.55
warming
-0.55
__":
-0.54
Deja
-0.53
__(/*!
-0.53
blended
-0.53
banho
-0.53
POSITIVE LOGITS
hammer
1.16
axe
1.15
spoon
1.15
knife
1.14
sword
1.13
shovel
1.08
pencil
1.02
baton
1.01
Knife
1.01
Axe
0.99
Activations Density 0.644%