INDEX
Explanations
references to political parties and local geographical details associated with them
New Auto-Interp
Negative Logits
German
-0.18
Berlin
-0.17
Germany
-0.17
German
-0.17
æ³¥
-0.17
Germany
-0.16
Germans
-0.16
Berlin
-0.16
okin
-0.16
Lutheran
-0.16
POSITIVE LOGITS
Vienna
0.26
Austria
0.21
edl
0.21
Austrian
0.21
Rupert
0.20
Graz
0.20
Wi
0.19
ustria
0.19
ndl
0.18
Sty
0.18
Activations Density 0.018%