INDEX
Explanations
mentions of government positions like "Secretary"
instances of the word "Secretary" in various contexts
New Auto-Interp
Negative Logits
river
-0.68
MQ
-0.65
orsi
-0.65
emp
-0.64
brim
-0.63
ILLE
-0.63
Predators
-0.62
Tang
-0.59
irc
-0.59
ERO
-0.57
POSITIVE LOGITS
chair
0.88
general
0.86
General
0.83
secretary
0.82
Secretary
0.80
osate
0.78
uty
0.77
secretaries
0.74
General
0.74
Secretary
0.71
Activations Density 0.026%