INDEX
Explanations
phrases indicating separation or distance from family, nature, and other environments
New Auto-Interp
Negative Logits
ontvangst
-0.16
lÃŃÄį
-0.15
خرÙī
-0.15
ocy
-0.15
462
-0.14
hs
-0.14
ίοÏĤ
-0.14
coles
-0.14
EditingStyle
-0.14
itti
-0.13
POSITIVE LOGITS
iginal
0.16
Spi
0.15
å¤ķ
0.15
èŃľ
0.15
pr
0.14
ään
0.14
progn
0.14
assin
0.14
ascus
0.14
processable
0.13
Activations Density 0.052%