INDEX
Explanations
references to American football teams, specifically the Pittsburgh Steelers and the Cincinnati Bengals
mentions of specific sports teams, particularly the Steelers and Bengals
New Auto-Interp
Negative Logits
ogy
-0.81
lly
-0.80
uras
-0.78
lled
-0.75
istically
-0.75
clusive
-0.73
clusively
-0.73
onymous
-0.72
judicial
-0.72
lining
-0.70
POSITIVE LOGITS
Steelers
1.19
Bengals
0.89
Raiders
0.86
Penguins
0.83
士
0.79
Steel
0.78
Packers
0.77
sburgh
0.76
rookie
0.73
linebacker
0.72
Activations Density 0.009%