INDEX
Explanations
mentions of medication or prescription drugs
New Auto-Interp
Negative Logits
beck
-0.16
el
-0.16
İng
-0.14
uluk
-0.14
onta
-0.14
loon
-0.13
elves
-0.13
phan
-0.13
驾
-0.13
hir
-0.13
POSITIVE LOGITS
fat
0.34
-fat
0.30
Fat
0.28
FAT
0.26
Fat
0.24
fats
0.24
fat
0.23
od
0.20
antim
0.20
BMI
0.18
Activations Density 0.000%