INDEX
Explanations
incidents related to sexual misconduct allegations
New Auto-Interp
Negative Logits
304
-0.17
286
-0.16
tg
-0.16
irie
-0.15
odp
-0.14
ussen
-0.14
gii
-0.14
abras
-0.14
feit
-0.14
ög
-0.14
POSITIVE LOGITS
ç´
0.16
pheres
0.15
PHA
0.15
NotAllowed
0.15
Rah
0.14
Sector
0.14
ylie
0.14
ascal
0.14
ocl
0.14
Miles
0.14
Activations Density 0.016%