INDEX
Explanations
titles and ranks associated with military personnel
New Auto-Interp
Negative Logits
icus
-0.19
otime
-0.16
addCriterion
-0.15
chte
-0.15
ite
-0.15
åĢĴ
-0.15
mine
-0.14
ITE
-0.14
away
-0.14
him
-0.14
POSITIVE LOGITS
colon
0.30
-Col
0.29
Colonel
0.27
-col
0.26
colon
0.25
Colon
0.23
Colon
0.23
.Cmd
0.22
-command
0.21
Col
0.20
Activations Density 0.013%