INDEX
Explanations
mentions of medical professionals, specifically doctors
what doctors do
New Auto-Interp
Negative Logits
fomentar
-0.47
iż
-0.47
Eisenberg
-0.46
Quig
-0.46
Contenu
-0.45
Guen
-0.44
brief
-0.44
새로운
-0.43
we
-0.43
wezig
-0.43
POSITIVE LOGITS
doctor
1.70
doctors
1.67
Doctors
1.59
Doctors
1.52
doctors
1.49
doctor
1.48
Doctor
1.47
Doctor
1.46
DOCTOR
1.36
DOCTOR
1.15
Activations Density 0.003%