INDEX
Explanations
references to various types of sports injuries
New Auto-Interp
Negative Logits
å¼ı
-0.17
oman
-0.16
TestingModule
-0.16
uhan
-0.16
mour
-0.15
olver
-0.15
tum
-0.14
UGH
-0.14
Burl
-0.14
ugh
-0.13
POSITIVE LOGITS
inet
0.16
ir
0.15
homo
0.15
Anc
0.15
cartel
0.15
оÑĢд
0.15
á»ı
0.14
iplinary
0.14
иÑģлов
0.14
anc
0.14
Activations Density 0.023%