INDEX
Explanations
references to sports teams
mentions of "team" and its variations across the text
New Auto-Interp
Negative Logits
trigger
-0.76
tml
-0.76
imentary
-0.75
Accessory
-0.74
drip
-0.73
ibrary
-0.72
ously
-0.68
rency
-0.67
aukee
-0.66
Crime
-0.66
POSITIVE LOGITS
mates
1.03
mates
0.92
rons
0.86
captain
0.81
Alic
0.79
mate
0.79
motto
0.77
coached
0.77
disbanded
0.77
manager
0.76
Activations Density 0.054%