INDEX
Explanations
references to plant-based diets and related advice
New Auto-Interp
Negative Logits
ãĥĥãĥī
-0.16
ÑĩеÑģ
-0.15
offee
-0.15
arpa
-0.15
ÑĤим
-0.15
ãİ
-0.14
Golf
-0.14
alink
-0.14
bred
-0.14
pei
-0.14
POSITIVE LOGITS
plant
0.50
vegan
0.47
Plant
0.42
veg
0.41
plant
0.41
Vegan
0.40
Plant
0.38
animal
0.37
ve
0.37
vegetarian
0.35
Activations Density 0.075%