INDEX
Explanations
references to a specific individual or entity related to a last name or title
New Auto-Interp
Negative Logits
nos
-0.18
iom
-0.17
s
-0.17
Nä
-0.15
ilot
-0.15
ugs
-0.15
ugal
-0.14
nám
-0.14
viar
-0.14
Commerce
-0.14
POSITIVE LOGITS
ning
0.28
NING
0.25
ns
0.23
der
0.22
icz
0.20
ne
0.20
NST
0.20
ther
0.19
æ¯Ľ
0.18
ders
0.18
Activations Density 0.009%