INDEX
Explanations
references to competitive events and sporting activities
New Auto-Interp
Negative Logits
Ñĥй
-0.18
Král
-0.17
ugu
-0.16
Jag
-0.15
cil
-0.14
tower
-0.14
aptor
-0.13
enta
-0.13
Ń
-0.13
total
-0.13
POSITIVE LOGITS
anches
0.15
wort
0.15
_ISO
0.14
AEA
0.14
.hw
0.14
isky
0.14
kea
0.14
اÙħÛĮÙĨ
0.14
EATURE
0.14
hend
0.14
Activations Density 0.018%