INDEX
Explanations
phrases related to injuries and health in sports
New Auto-Interp
Negative Logits
Champ
-0.69
à¦
-0.66
arge
-0.65
pedia
-0.64
crypt
-0.64
INESS
-0.62
violates
-0.61
harm
-0.61
Tweet
-0.61
mask
-0.61
POSITIVE LOGITS
introducing
0.74
his
0.71
the
0.70
course
0.68
wanting
0.68
those
0.67
elia
0.67
relations
0.67
critics
0.65
è£ıè
0.64
Activations Density 0.068%