INDEX
Explanations
references to medical conditions related to obesity
references to obesity and its related terminology
New Auto-Interp
Negative Logits
sparks
-0.72
spark
-0.71
hend
-0.70
pell
-0.67
salv
-0.66
Ron
-0.65
Phoenix
-0.65
spe
-0.64
unity
-0.64
ua
-0.64
POSITIVE LOGITS
obesity
3.56
Obesity
3.04
obese
2.74
esity
2.09
overweight
2.00
Diabetes
1.73
adip
1.72
diabetes
1.69
BMI
1.63
leptin
1.62
Activations Density 0.024%