INDEX
Explanations
mentions of educational legislation and related events
New Auto-Interp
Negative Logits
ìŀ¥ìĿ´
-0.14
ÏĦεÏħ
-0.14
ÄIJT
-0.14
iami
-0.14
---</
-0.14
èĪĮ
-0.13
ÑĤап
-0.13
.ali
-0.13
_',
-0.13
ardu
-0.13
POSITIVE LOGITS
âĢ¢
0.77
âĢ¢
0.67
cdot
0.47
.âĢ¢
0.46
·
0.39
âĢ¢↵↵
0.38
ãĥ»
0.36
ãĥ»
0.33
·
0.32
Âķ
0.32
Activations Density 0.044%