INDEX
Explanations
references to sports figures and individuals' achievements
New Auto-Interp
Negative Logits
bezeichneter
-0.66
évaluateur
-0.55
Guests
-0.53
baru
-0.52
στη
-0.52
لينك
-0.52
guesthouse
-0.51
DIPSETTING
-0.51
(:)
-0.51
mín
-0.50
POSITIVE LOGITS
NameInMap
0.65
MVP
0.64
noqa
0.63
teammate
0.59
teammates
0.59
superstar
0.57
CompilerServices
0.53
poy
0.51
ardom
0.51
puncak
0.51
Activations Density 0.288%