INDEX
Explanations
references to player statistics and performances in sports
New Auto-Interp
Negative Logits
enson
-0.16
explos
-0.16
ecided
-0.16
ruba
-0.15
nás
-0.15
MetroFramework
-0.15
edor
-0.15
ipur
-0.15
ikal
-0.15
redo
-0.14
POSITIVE LOGITS
dual
0.15
ust
0.14
ble
0.14
_defs
0.14
lv
0.14
Forgot
0.13
plate
0.13
gle
0.13
ichte
0.13
olen
0.13
Activations Density 0.046%