INDEX
Explanations
possessive pronouns related to relationships or family
New Auto-Interp
Negative Logits
ór
-0.16
ially
-0.15
rn
-0.15
ninger
-0.14
iale
-0.14
uby
-0.14
_ELEMENT
-0.14
Prov
-0.14
Ella
-0.14
yscale
-0.14
POSITIVE LOGITS
atinum
0.16
Braun
0.15
eut
0.15
intree
0.15
Gund
0.14
ewater
0.14
raquo
0.14
.$.
0.13
oningen
0.13
emed
0.13
Activations Density 0.029%