INDEX
Explanations
references to sports practices and training activities
New Auto-Interp
Negative Logits
#
-0.19
ÙĦاØŃ
-0.17
emes
-0.16
pra
-0.15
REFIX
-0.15
$MESS
-0.14
CONS
-0.14
ekim
-0.14
éĹŃ
-0.14
xcc
-0.14
POSITIVE LOGITS
376
0.15
orsk
0.15
bbe
0.15
inois
0.15
oup
0.14
Phelps
0.14
yn
0.14
y
0.14
orio
0.14
mole
0.14
Activations Density 0.010%