INDEX
Explanations
references to officiating and decision-making in sports
New Auto-Interp
Negative Logits
uÄŁ
-0.15
otto
-0.15
鼶
-0.14
_HINT
-0.14
ampaign
-0.14
'..',
-0.13
raquo
-0.13
_shutdown
-0.13
cuffs
-0.13
Coloring
-0.13
POSITIVE LOGITS
ersed
0.16
Dw
0.15
änd
0.15
tae
0.14
gba
0.14
kea
0.14
Valk
0.14
gii
0.14
overturned
0.14
542
0.14
Activations Density 0.035%