INDEX
Explanations
mentions of military units and battalions in historical contexts
New Auto-Interp
Negative Logits
onse
-0.15
disag
-0.14
_DX
-0.14
æŃ²
-0.14
ugas
-0.14
umbed
-0.14
воÑĢ
-0.14
ãģľ
-0.14
ulas
-0.14
овиÑĩ
-0.13
POSITIVE LOGITS
906
0.15
utom
0.15
éģĵ
0.15
thouse
0.15
raph
0.15
áº
0.14
ronic
0.14
yth
0.14
atha
0.14
Kit
0.14
Activations Density 0.058%