INDEX
Explanations
words related to playing and participation in sports or games
New Auto-Interp
Negative Logits
AMPL
-0.17
ghan
-0.16
spath
-0.15
zend
-0.15
romo
-0.15
ียà¸ĩ
-0.14
doch
-0.14
hir
-0.14
/ay
-0.14
neas
-0.14
POSITIVE LOGITS
arella
0.16
calar
0.14
MOUSE
0.14
Rosenberg
0.14
µ
0.14
stuff
0.14
iten
0.14
velocity
0.14
haft
0.13
afe
0.13
Activations Density 0.042%