INDEX
Explanations
terms related to education, civil rights, politics, and social justice issues
New Auto-Interp
Negative Logits
ically
-0.17
ç°
-0.14
uh
-0.14
Ùį
-0.13
:č↵
-0.13
ấy
-0.13
akin
-0.13
夫
-0.13
ISED
-0.13
Outcome
-0.13
POSITIVE LOGITS
Uncategorized
0.18
/misc
0.17
misc
0.16
пиÑĤ
0.15
&
0.15
ertiary
0.15
misc
0.14
bject
0.14
raquo
0.14
Misc
0.14
Activations Density 0.281%