INDEX
Explanations
mentions of specific dates or locations, particularly in the context of events in Africa
New Auto-Interp
Negative Logits
bling
-0.17
ogie
-0.17
lier
-0.17
ogg
-0.16
istically
-0.15
ovie
-0.15
decom
-0.15
ikal
-0.15
liest
-0.15
elling
-0.14
POSITIVE LOGITS
upt
0.18
icot
0.18
era
0.18
athom
0.16
inger
0.16
IDGE
0.16
ault
0.16
ão
0.15
ERA
0.15
ekim
0.15
Activations Density 0.033%