INDEX
Explanations
food items and dishes with a focus on their preparation and ingredients
New Auto-Interp
Negative Logits
majority
-0.14
advantage
-0.14
ä½Ļ
-0.14
sak
-0.14
avin
-0.13
573
-0.13
ÏĮγ
-0.13
Bakery
-0.13
rzy
-0.13
Spo
-0.13
POSITIVE LOGITS
ifix
0.17
aris
0.16
olith
0.16
swith
0.16
arma
0.15
-style
0.15
-making
0.14
ÑĤоÑĦ
0.14
served
0.14
.createFrom
0.14
Activations Density 0.103%