INDEX
Explanations
references to historical industries and their significance
New Auto-Interp
Negative Logits
گاب
-0.14
668
-0.14
xx
-0.13
kvinna
-0.13
ham
-0.13
arg
-0.13
crest
-0.13
Mana
-0.13
onta
-0.13
zar
-0.13
POSITIVE LOGITS
Danish
0.38
Dan
0.36
Dan
0.34
dan
0.31
丹
0.30
DAN
0.30
dan
0.28
Dans
0.28
.dk
0.28
Denmark
0.27
Activations Density 0.007%