INDEX
Explanations
references to educational roles or positions, particularly lectures and lecturers
New Auto-Interp
Negative Logits
istically
-0.18
oky
-0.18
arily
-0.17
von
-0.15
olean
-0.15
/Home
-0.15
agem
-0.14
imeType
-0.14
elters
-0.14
atsby
-0.14
POSITIVE LOGITS
urers
0.30
urer
0.25
ures
0.24
ern
0.21
uring
0.19
tte
0.17
erm
0.17
io
0.17
eur
0.17
chas
0.16
Activations Density 0.006%