INDEX
Explanations
proper nouns related to sports teams, particularly the Detroit Tigers
mentions of the "Tigers"
New Auto-Interp
Negative Logits
aleigh
-0.80
uters
-0.79
trak
-0.77
sth
-0.75
abil
-0.71
ibel
-0.71
ersion
-0.69
utherford
-0.69
UTERS
-0.68
pron
-0.67
POSITIVE LOGITS
Tigers
1.53
tigers
1.09
Tiger
1.04
tiger
0.94
emonium
0.92
Pistons
0.90
igers
0.89
Sharks
0.85
Lions
0.78
resil
0.78
Activations Density 0.009%