INDEX
Explanations
references to ice cream and related treats
New Auto-Interp
Negative Logits
bread
-0.19
gravy
-0.18
ente
-0.17
enta
-0.17
amina
-0.16
cooking
-0.15
wines
-0.15
frying
-0.15
champagne
-0.15
lej
-0.15
POSITIVE LOGITS
ice
0.42
Ice
0.38
Ice
0.33
ice
0.31
åĨ°
0.25
ICE
0.25
ices
0.25
ICE
0.23
cone
0.23
scoop
0.23
Activations Density 0.040%