INDEX
Explanations
references to sports teams' names, particularly 'Wildcats'
references to the Wildcats and players associated with them
New Auto-Interp
Negative Logits
orius
-0.73
ש
-0.71
atio
-0.70
raught
-0.70
aneous
-0.70
à¥
-0.68
atis
-0.68
light
-0.67
ument
-0.67
OND
-0.66
POSITIVE LOGITS
eus
0.93
cius
0.89
elsius
0.84
daq
0.76
ollah
0.76
rontal
0.75
hammad
0.72
airo
0.71
ities
0.69
iliary
0.69
Activations Density 0.050%