INDEX
Explanations
phrases related to sports teams
mentions of sports teams
New Auto-Interp
Negative Logits
Accessory
-0.82
dit
-0.76
ously
-0.74
tar
-0.74
ibrary
-0.73
Tablet
-0.72
ariat
-0.69
tain
-0.65
bush
-0.65
td
-0.65
POSITIVE LOGITS
peak
0.96
vying
0.85
heet
0.81
competing
0.81
ete
0.80
ubs
0.79
liquid
0.75
hedral
0.74
etter
0.74
fielded
0.73
Activations Density 0.056%