INDEX
Explanations
references to teachers and educational contexts
New Auto-Interp
Negative Logits
@student
-0.21
Universities
-0.20
大åѸ
-0.20
universities
-0.19
大åѦ
-0.19
Colleges
-0.18
College
-0.17
Scholar
-0.16
undergrad
-0.16
colleges
-0.16
POSITIVE LOGITS
principal
0.36
substitute
0.35
Principal
0.32
principal
0.31
Substitute
0.31
guidance
0.31
principals
0.30
Guidance
0.29
teacher
0.29
Principal
0.29
Activations Density 0.150%