INDEX
Explanations
occurrences of statistical scores related to sports events
New Auto-Interp
Negative Logits
Gut
-0.16
δÏģα
-0.15
tember
-0.14
uchs
-0.14
elsen
-0.14
ooter
-0.14
governing
-0.14
andler
-0.14
rou
-0.14
amenti
-0.14
POSITIVE LOGITS
nv
0.17
key
0.16
allon
0.15
Paperback
0.15
horns
0.15
ODY
0.15
ัà¸ķ
0.14
å¸
0.14
atti
0.14
624
0.14
Activations Density 0.062%