INDEX
Explanations
references to specific names and notable figures
New Auto-Interp
Negative Logits
Cob
-0.71
מוצ
-0.70
Chel
-0.69
oulder
-0.66
Ling
-0.63
GOB
-0.63
Irvin
-0.63
Marin
-0.61
переди
-0.61
dib
-0.60
POSITIVE LOGITS
на
1.18
بوابة
1.02
На
0.94
На
0.93
ViewFeatures
0.91
Auf
0.90
Na
0.90
Berna
0.90
PerformLayout
0.88
Naidu
0.88
Activations Density 0.054%