INDEX
Explanations
historical and political analysis
New Auto-Interp
Negative Logits
может
0.77
ibel
0.76
needful
0.70
when
0.70
swabs
0.70
ocasi
0.70
when
0.70
Bayram
0.68
angi
0.68
がない
0.68
POSITIVE LOGITS
ideology
1.07
mismanagement
1.03
propaganda
1.02
historians
1.02
giai
0.99
hardships
0.98
resentment
0.98
debated
0.98
injustices
0.98
politica
0.97
Activations Density 0.161%