INDEX
Explanations
imperatives and expressions of necessity or obligation
New Auto-Interp
Negative Logits
ymi
-0.16
azo
-0.15
Sad
-0.15
است
-0.15
κει
-0.14
ctal
-0.14
oct
-0.14
ting
-0.14
одо
-0.14
سات
-0.13
POSITIVE LOGITS
ãĥ³ãĤº
0.18
oine
0.15
_HW
0.14
arrants
0.14
rome
0.14
Ñĥж
0.14
éł
0.14
elda
0.13
arte
0.13
olan
0.13
Activations Density 0.332%