INDEX
Explanations
mentions of education policy and governance-related terms
New Auto-Interp
Negative Logits
_
-0.16
.asp
-0.15
Boss
-0.14
izo
-0.14
704
-0.14
aler
-0.13
issors
-0.13
VRT
-0.13
avirus
-0.13
_(
-0.13
POSITIVE LOGITS
ahn
0.16
{{--<0.15
teh
0.15
æ®
0.15
nex
0.14
tej
0.14
أجÙĦ
0.13
fuck
0.13
Mapped
0.13
ukan
0.13
Activations Density 0.000%