INDEX
Explanations
names of historical figures and their associated professions
New Auto-Interp
Negative Logits
propOrder
-0.63
StoryboardSegue
-0.51
kasarigan
-0.48
Meksiku
-0.48
ThroughAttribute
-0.47
Personendaten
-0.46
correctes
-0.45
Thacker
-0.45
nahilalakip
-0.45
Wray
-0.44
POSITIVE LOGITS
German
0.95
Germany
0.94
Germans
0.91
german
0.84
Austria
0.83
Germany
0.82
Austrian
0.82
GERMAN
0.82
German
0.81
Berlin
0.80
Activations Density 14.963%