INDEX
Explanations
references to soldiers and military personnel
New Auto-Interp
Negative Logits
elay
-0.15
hin
-0.15
gger
-0.14
ï¸ı
-0.14
ATER
-0.14
æķı
-0.14
.gwt
-0.14
ISTA
-0.14
//////////////////////////////////////////////////////////////////////
-0.13
Incident
-0.13
POSITIVE LOGITS
ernet
0.16
anzi
0.15
anuts
0.15
IFORM
0.14
afen
0.14
isch
0.13
üb
0.13
otti
0.13
.sun
0.13
iniz
0.13
Activations Density 0.020%