INDEX
Explanations
emotional expressions related to vulnerability and support in relationships
New Auto-Interp
Negative Logits
.updateDynamic
-0.14
Rim
-0.14
iesel
-0.14
.infinity
-0.14
Hubb
-0.13
ÏĦÏģο
-0.13
æĤł
-0.13
tif
-0.13
олеÑĤ
-0.13
FRING
-0.13
POSITIVE LOGITS
candid
0.47
cand
0.45
honest
0.44
honesty
0.44
vulnerability
0.40
transparent
0.39
vulner
0.38
Honest
0.38
transparency
0.38
frank
0.37
Activations Density 0.388%