INDEX
Explanations
references to large populations or statistics related to literacy and education
New Auto-Interp
Negative Logits
gu
-0.16
á»ĥ
-0.16
alfa
-0.15
yon
-0.14
cntl
-0.14
mlink
-0.14
imir
-0.14
ierce
-0.14
opr
-0.14
ophys
-0.14
POSITIVE LOGITS
Hess
0.15
ëĦ·
0.14
ijľ
0.14
oogle
0.14
/token
0.14
rán
0.14
lobals
0.14
Rot
0.14
emploi
0.14
bro
0.14
Activations Density 0.055%