INDEX
Explanations
phrases related to food ingredients and cooking methods
New Auto-Interp
Negative Logits
ulle
-0.17
↵↵
-0.17
大åħ¨
-0.16
UTERS
-0.15
OTTOM
-0.15
olare
-0.15
deen
-0.15
ÑĢин
-0.15
asses
-0.15
lle
-0.15
POSITIVE LOGITS
-bar
0.16
Representation
0.15
//~
0.15
dio
0.15
cru
0.15
representation
0.15
ikon
0.15
Representation
0.14
971
0.14
ptron
0.14
Activations Density 0.189%