INDEX
Explanations
references to hockey and its players’ performance
New Auto-Interp
Negative Logits
Jaune
-0.16
Auss
-0.14
distances
-0.14
hani
-0.14
æģ¯
-0.14
اÙĪÙĨ
-0.13
jav
-0.13
XX
-0.13
bows
-0.13
Leaks
-0.13
POSITIVE LOGITS
NHL
0.25
hockey
0.23
Hockey
0.22
ice
0.20
skating
0.19
puck
0.18
ertz
0.17
Ice
0.17
ockey
0.16
skate
0.16
Activations Density 0.216%