INDEX
Explanations
mentions of a specific sports team, the Buffalo Bills
mentions of the Buffalo Bills
New Auto-Interp
Negative Logits
odan
-0.75
linear
-0.72
ogen
-0.68
isse
-0.67
humanoid
-0.65
tent
-0.64
sem
-0.64
distributed
-0.63
inder
-0.63
ø
-0.61
POSITIVE LOGITS
Bills
4.12
Sabres
2.28
Dolphins
1.77
Bengals
1.70
Texans
1.64
Jaguars
1.60
Chargers
1.57
Buffalo
1.56
Colts
1.50
Jets
1.49
Activations Density 0.014%