INDEX
Explanations
references to historical events and figures related to World War II and the Holocaust
New Auto-Interp
Negative Logits
betweenstory
-0.76
expandindo
-0.69
delwed
-0.65
ConstraintMaker
-0.65
rungsseite
-0.63
autorytatywna
-0.61
препратки
-0.60
CanadaChoose
-0.60
锈钢
-0.60
intios
-0.60
POSITIVE LOGITS
Serbian
0.68
Serbia
0.65
Adriatic
0.62
Croatian
0.61
Belgrade
0.60
Montenegro
0.57
Namely
0.56
Slovenian
0.52
Yugoslav
0.51
Croatia
0.50
Activations Density 0.189%