INDEX
Explanations
phrases related to obligation and necessity
New Auto-Interp
Negative Logits
ezi
-0.17
deniz
-0.16
ué
-0.15
Bush
-0.14
872
-0.14
omp
-0.14
_simps
-0.14
zw
-0.14
quee
-0.14
Ùħؤ
-0.14
POSITIVE LOGITS
AGR
0.15
mán
0.14
extra
0.14
exual
0.14
dana
0.14
ynos
0.14
actable
0.14
icing
0.13
sil
0.13
ivia
0.13
Activations Density 0.304%