INDEX
Explanations
references to medical professionals, particularly physicians
references to physicians and medical practitioners
New Auto-Interp
Negative Logits
eworld
-0.79
flag
-0.75
yrinth
-0.71
Orwell
-0.71
urat
-0.69
Territories
-0.69
nings
-0.69
eat
-0.68
footed
-0.68
runners
-0.68
POSITIVE LOGITS
physician
1.13
practitioner
1.04
physicians
0.98
doctor
0.94
prescribing
0.88
psychiatrist
0.88
prescriptions
0.85
examiner
0.85
care
0.85
surgeon
0.83
Activations Density 0.015%