INDEX
Explanations
mentions of Vladimir Putin and related historical references
New Auto-Interp
Negative Logits
elly
-0.16
iola
-0.16
až
-0.15
market
-0.15
INET
-0.15
marketplace
-0.15
unos
-0.15
Crosby
-0.15
stown
-0.15
uries
-0.14
POSITIVE LOGITS
imir
0.32
Putin
0.25
islav
0.23
Vladim
0.20
mir
0.20
ilen
0.18
Lenin
0.18
isl
0.17
Guerrero
0.17
imer
0.17
Activations Density 0.006%