INDEX
Explanations
words related to medical doctors
mentions of a specific name or term associated with someone's surname
New Auto-Interp
Negative Logits
PDATE
-0.73
ITAL
-0.70
Flavoring
-0.70
âĸ¬
-0.67
âĸ¬âĸ¬
-0.67
exha
-0.66
quo
-0.66
rano
-0.63
RED
-0.61
Oak
-0.61
POSITIVE LOGITS
ipop
1.33
oning
0.96
ieu
0.95
inson
0.92
iard
0.90
ocations
0.89
ega
0.88
sburgh
0.88
ocks
0.88
oyd
0.87
Activations Density 0.012%