INDEX
Explanations
terms related to body weight and physical appearance
references to body weight and related conditions
New Auto-Interp
Negative Logits
Gas
-0.68
DCS
-0.67
âĸ¬
-0.66
Noir
-0.66
ource
-0.65
gency
-0.65
oral
-0.65
INST
-0.65
onto
-0.64
ILA
-0.64
POSITIVE LOGITS
overweight
1.10
obese
0.86
esity
0.85
idious
0.76
obesity
0.74
eki
0.73
stable
0.73
gorilla
0.72
rition
0.71
nesses
0.68
Activations Density 0.013%