INDEX
Explanations
references to locations, specifically focusing on the city of Moscow
references to Moscow and its associated context
New Auto-Interp
Negative Logits
âĢ¢âĢ¢âĢ¢âĢ¢
-0.80
ORGE
-0.79
cause
-0.77
terson
-0.73
++++
-0.72
ministic
-0.72
ROM
-0.72
inals
-0.71
pir
-0.70
lihood
-0.70
POSITIVE LOGITS
rall
1.04
Lumpur
0.97
annexed
0.93
Moscow
0.85
Kremlin
0.85
Federation
0.80
bureau
0.79
iets
0.78
ascus
0.77
bloc
0.74
Activations Density 0.017%