INDEX
Explanations
mentions of kitchens and kitchen-related features
New Auto-Interp
Negative Logits
e
-0.16
645
-0.15
tors
-0.15
-0.14
594
-0.14
eed
-0.14
s
-0.14
441
-0.14
oothing
-0.14
sus
-0.14
POSITIVE LOGITS
etics
0.16
İ
0.15
iser
0.15
ete
0.15
idata
0.15
ỳ
0.14
lad
0.14
.mj
0.14
/bar
0.14
erce
0.14
Activations Density 0.019%