INDEX
Explanations
words related to education or educational context
New Auto-Interp
Negative Logits
.har
-0.18
ÑıÑģ
-0.17
ptal
-0.14
alÄ±ÅŁ
-0.14
gs
-0.14
lass
-0.14
eer
-0.14
ÚĨÙĩ
-0.14
las
-0.14
оÑģÑĤ
-0.14
POSITIVE LOGITS
ational
0.21
ATIONAL
0.18
acional
0.17
ators
0.17
ationally
0.17
uela
0.15
643
0.15
maz
0.15
ication
0.15
ación
0.15
Activations Density 0.011%