INDEX
Explanations
keywords related to health issues and medical procedures
topics related to health and illness
New Auto-Interp
Negative Logits
asikan
-0.48
didik
-0.46
marketplace
-0.46
Rape
-0.45
lèvres
-0.44
ündig
-0.44
pouce
-0.43
rangs
-0.43
boste
-0.42
incest
-0.42
POSITIVE LOGITS
health
0.92
health
0.82
illness
0.75
HEALTH
0.73
Health
0.72
Health
0.71
🏥
0.71
hospitalization
0.69
HEALTH
0.67
hospital
0.66
Activations Density 0.382%