INDEX
Explanations
mentions of specific surnames, likely of Polish origin
mentions of specific surnames or names within the text
New Auto-Interp
Negative Logits
ific
-0.75
icas
-0.74
ICA
-0.74
orians
-0.71
ãĥ¼ãĥ³
-0.71
nard
-0.68
istor
-0.66
ugu
-0.65
ãĥ¼ãĥĨ
-0.65
eric
-0.65
POSITIVE LOGITS
inski
0.97
ynski
0.82
ski
0.82
owski
0.81
itsch
0.81
Brothers
0.77
orld
0.76
sie
0.75
Syndicate
0.73
ansky
0.73
Activations Density 0.045%