INDEX
Explanations
references to missing artworks, particularly in historical contexts
New Auto-Interp
Negative Logits
докÑĥм
-0.20
пÑĢоÑĦеÑģÑģионалÑĮ
-0.17
бÑĥма
-0.17
oman
-0.16
ÑģобÑĭ
-0.15
dim
-0.15
поба
-0.14
bower
-0.14
ار
-0.14
porter
-0.14
POSITIVE LOGITS
ÑģевеÑĢ
0.18
Sever
0.17
Territories
0.17
зап
0.16
маÑģÑģив
0.15
territor
0.15
СевеÑĢ
0.15
territories
0.15
sel
0.15
zoekt
0.15
Activations Density 0.016%