INDEX
Explanations
pronouns and possessive adjectives indicating personal relationships and emotional connections
New Auto-Interp
Negative Logits
нова
-0.16
.normalized
-0.16
imore
-0.16
æ¾
-0.15
RIPT
-0.15
Ãło
-0.15
udad
-0.15
ATUS
-0.14
mania
-0.14
road
-0.14
POSITIVE LOGITS
atri
0.15
domin
0.14
омÑĥ
0.14
ollo
0.14
Relations
0.14
ustralian
0.14
gum
0.14
relations
0.13
ά
0.13
ãĥ³ãĤ¿
0.13
Activations Density 0.628%