INDEX
Explanations
characteristics related to food, specifically dish descriptions and culinary contexts
New Auto-Interp
Negative Logits
rag
-0.21
linger
-0.19
erokee
-0.16
uters
-0.15
CardBody
-0.15
regor
-0.15
edBy
-0.14
bib
-0.14
olu
-0.14
erce
-0.14
POSITIVE LOGITS
both
0.15
oret
0.15
840
0.14
both
0.14
бÑĥдÑĮ
0.13
ayah
0.13
Janet
0.13
ay
0.13
680
0.12
plits
0.12
Activations Density 0.115%