INDEX
Explanations
Iranian politics and governance
New Auto-Interp
Negative Logits
mlijeka
0.99
børn
0.88
samoglas
0.87
dźwię
0.87
þei
0.86
simonsen
0.86
ameryka
0.86
𝐪
0.84
kę
0.84
događ
0.83
POSITIVE LOGITS
به
1.09
در
1.07
1.06
0.99
Iran
0.96
Iran
0.95
و
0.94
Iranian
0.94
پ
0.93
از
0.93
Activations Density 0.006%