INDEX
Explanations
various forms of nouns indicating ranking or achievement
New Auto-Interp
Negative Logits
DataExchange
-0.16
ikan
-0.16
rych
-0.15
ips
-0.14
ieten
-0.14
stant
-0.14
/member
-0.14
usan
-0.14
idor
-0.14
antal
-0.14
POSITIVE LOGITS
otros
0.16
åŃĹ
0.15
pornstar
0.14
iyas
0.14
avec
0.13
lee
0.13
IDb
0.13
others
0.13
scarcely
0.13
ustralian
0.13
Activations Density 0.063%