INDEX
Explanations
references to alumni and alumni associations
New Auto-Interp
Negative Logits
ape
-0.19
chter
-0.17
lington
-0.16
Gerr
-0.15
Gly
-0.14
ger
-0.14
apas
-0.14
ób
-0.14
fried
-0.14
iar
-0.14
POSITIVE LOGITS
sie
0.15
outh
0.15
uzzi
0.15
аÑĤков
0.15
IMO
0.14
ê¸ī
0.14
atic
0.14
ktop
0.14
tep
0.14
Nurs
0.13
Activations Density 0.006%