INDEX
Explanations
mentions of specific food items or dishes
New Auto-Interp
Negative Logits
Neg
-0.15
Į
-0.14
ipmap
-0.14
iggins
-0.14
ilm
-0.14
260
-0.14
仪
-0.14
yi
-0.14
RLF
-0.14
iness
-0.14
POSITIVE LOGITS
aku
0.17
elong
0.17
enta
0.16
oui
0.16
Dress
0.16
èŤ
0.16
uto
0.15
endwhile
0.15
ERCHANT
0.15
ercul
0.15
Activations Density 0.057%