INDEX
Explanations
phrases or quotes related to political declarations and actions
New Auto-Interp
Negative Logits
atee
-0.16
prec
-0.14
caling
-0.14
Vide
-0.14
CRET
-0.14
forg
-0.14
Nimbus
-0.14
negoci
-0.13
erdem
-0.13
mitter
-0.13
POSITIVE LOGITS
óng
0.16
assin
0.16
semiclass
0.15
Pir
0.14
Farms
0.14
fatt
0.14
PIO
0.14
elles
0.14
antage
0.14
ipa
0.14
Activations Density 0.008%