INDEX
Explanations
mentions of military operations and their numbered designations
New Auto-Interp
Negative Logits
quer
-0.16
айд
-0.16
akan
-0.15
akit
-0.15
alam
-0.14
ilk
-0.14
gor
-0.14
[OF
-0.14
/server
-0.14
į¨
-0.14
POSITIVE LOGITS
dead
0.15
alent
0.15
defs
0.15
ê´Ģ
0.15
adh
0.14
ãĥ³ãĥĩãĤ£
0.14
phans
0.14
uw
0.14
jh
0.13
алеж
0.13
Activations Density 0.026%