INDEX
Explanations
words related to dairy products
references to butter
New Auto-Interp
Negative Logits
vernment
-0.93
Exile
-0.78
SPONSORED
-0.68
ļé
-0.68
ostics
-0.67
debtor
-0.67
Naz
-0.67
Centauri
-0.66
Citizen
-0.65
Jinn
-0.63
POSITIVE LOGITS
cream
1.43
cup
1.21
flies
1.15
beer
1.04
fat
0.99
finger
0.98
nut
0.97
bowl
0.95
maid
0.94
stroke
0.94
Activations Density 0.018%