INDEX
Explanations
mentions of colleges and universities
references to college-related topics or institutions
New Auto-Interp
Negative Logits
ãĥĩ
-0.83
oeuv
-0.78
Horus
-0.75
mask
-0.74
®
-0.71
Tracker
-0.69
Toro
-0.69
ãĥ¢
-0.68
eny
-0.65
mir
-0.64
POSITIVE LOGITS
college
3.60
college
2.77
College
2.70
colleges
2.49
College
2.43
collegiate
2.30
university
2.16
Colleges
1.94
undergrad
1.80
school
1.76
Activations Density 0.016%