INDEX
Explanations
expressions of enjoyment and sharing related to food experiences
New Auto-Interp
Negative Logits
dough
-0.16
onian
-0.15
Cake
-0.15
brewed
-0.15
Brew
-0.15
Chocolate
-0.15
chocolate
-0.15
_PKG
-0.14
Dough
-0.14
brewing
-0.14
POSITIVE LOGITS
Į
0.17
dinner
0.16
ewis
0.16
0.15
dish
0.15
acompan
0.15
0.14
fibre
0.14
ÄijÄ©a
0.14
ìĺ¤íĽĦ
0.14
Activations Density 0.121%