INDEX
Explanations
references to cultural and historical elements
New Auto-Interp
Negative Logits
ombo
-0.18
bát
-0.16
vise
-0.15
chein
-0.15
ided
-0.15
átek
-0.15
*)((
-0.15
_BOUND
-0.14
smo
-0.14
distributed
-0.13
POSITIVE LOGITS
Stark
0.15
oppos
0.15
ãĤ¹ãĤ¯
0.14
ilik
0.14
concepts
0.14
namoro
0.14
arak
0.14
expelled
0.14
iele
0.14
Bram
0.14
Activations Density 0.093%