INDEX
Explanations
the presence of Spanish verbs, particularly forms of "ser" and "ir"
New Auto-Interp
Negative Logits
cher
-0.17
s
-0.16
avail
-0.15
ariat
-0.15
tte
-0.14
a
-0.14
regar
-0.14
328
-0.14
geois
-0.14
.ua
-0.14
POSITIVE LOGITS
Kul
0.14
ůl
0.14
scoped
0.14
stdin
0.13
eyh
0.13
eyse
0.13
adır
0.12
URA
0.12
abin
0.12
oma
0.12
Activations Density 0.044%