INDEX
Explanations
references to legal and social issues regarding personal rights
New Auto-Interp
Negative Logits
Plate
-0.15
plates
-0.15
æĿ¿
-0.15
çİĦ
-0.15
Buk
-0.15
plate
-0.14
allax
-0.14
Plate
-0.14
ida
-0.14
Booker
-0.14
POSITIVE LOGITS
Spears
0.42
Brit
0.35
conserv
0.33
Spe
0.30
Conserv
0.30
Brit
0.29
Spear
0.29
spe
0.26
-spe
0.23
brit
0.23
Activations Density 0.004%