INDEX
Explanations
expressions of apathy or disconnection from emotional situations
New Auto-Interp
Negative Logits
æĹħè¡Į
-0.17
ancock
-0.16
ambre
-0.16
Traits
-0.15
à¹Ģหล
-0.15
akest
-0.15
omap
-0.15
è¿ij
-0.14
andi
-0.14
.travel
-0.14
POSITIVE LOGITS
somehow
0.17
ita
0.16
Gilles
0.16
à¤Łà¤ķ
0.15
iane
0.15
uler
0.14
chu
0.14
ya
0.14
\V
0.14
Bes
0.14
Activations Density 0.099%