INDEX
Explanations
mentions or references to individuals with the title "Dr."
references to individuals with the title "Dr."
New Auto-Interp
Negative Logits
eers
-0.78
Leilan
-0.76
SHIP
-0.76
ISM
-0.71
chorus
-0.70
CHAT
-0.68
eering
-0.67
LOAD
-0.67
actionGroup
-0.66
Territories
-0.65
POSITIVE LOGITS
inks
1.15
inker
1.15
inking
1.10
ink
1.09
umin
1.09
unk
1.09
agger
1.04
ifts
1.01
udge
1.00
agic
0.99
Activations Density 0.018%