INDEX
Explanations
mentions of athletes and their roles in sports contexts
New Auto-Interp
Negative Logits
Hiring
-0.16
hiring
-0.15
ukan
-0.15
amble
-0.15
urai
-0.14
reff
-0.14
hires
-0.14
кÑĥ
-0.14
eref
-0.14
oze
-0.14
POSITIVE LOGITS
rotation
0.27
rotational
0.26
rotation
0.24
Rotation
0.24
starter
0.23
starters
0.23
rotations
0.23
rotated
0.23
spot
0.23
Rotation
0.22
Activations Density 0.147%