INDEX
Explanations
informal expressions of opinion and personal feelings
New Auto-Interp
Negative Logits
øy
-0.15
elder
-0.14
crop
-0.14
лиз
-0.14
ulp
-0.14
pres
-0.14
asley
-0.14
iT
-0.13
ibo
-0.13
ää
-0.13
POSITIVE LOGITS
obre
0.16
unca
0.14
.variant
0.14
entic
0.14
ģm
0.13
åħī
0.13
erah
0.13
beg
0.13
внеÑģ
0.13
_entities
0.13
Activations Density 0.116%