INDEX
Explanations
references to students and student organizations
New Auto-Interp
Negative Logits
bach
-0.17
aul
-0.16
udi
-0.15
students
-0.15
askets
-0.15
ching
-0.15
kers
-0.14
schools
-0.14
Mansion
-0.14
cls
-0.14
POSITIVE LOGITS
athlete
0.18
-worker
0.18
athlete
0.17
body
0.17
Body
0.17
-led
0.16
aid
0.16
athletes
0.16
-run
0.16
services
0.16
Activations Density 0.020%