INDEX
Explanations
references to faculty members and staff within an educational context
New Auto-Interp
Negative Logits
ildo
-0.18
itta
-0.17
enas
-0.16
gis
-0.15
emies
-0.15
ingly
-0.15
-deals
-0.14
ammer
-0.14
<!--↵
-0.14
amak
-0.14
POSITIVE LOGITS
ground
0.18
396
0.17
ustr
0.16
ãĥ¥ãĥ¼
0.16
TextStyle
0.15
428
0.15
grounds
0.15
rary
0.14
GROUND
0.14
ilenames
0.14
Activations Density 0.006%