INDEX
Explanations
phrases related to sports rankings
references to runners and related terms in competitive contexts
New Auto-Interp
Negative Logits
olia
-0.88
umbn
-0.77
rification
-0.75
ILCS
-0.74
ropy
-0.72
illery
-0.72
arial
-0.71
ornia
-0.71
rox
-0.70
ogy
-0.69
POSITIVE LOGITS
ners
0.98
wear
0.94
swick
0.91
ways
0.88
runner
0.88
Runner
0.84
runners
0.79
bridge
0.78
gaard
0.77
runner
0.76
Activations Density 0.014%