INDEX
Explanations
topics related to stigma and mental health awareness
New Auto-Interp
Negative Logits
jej
-0.15
Pic
-0.15
PIC
-0.14
Preservation
-0.14
ãģ¤ãģ¶
-0.14
Hab
-0.14
ubic
-0.14
è²Ŀ
-0.13
ondo
-0.13
fahren
-0.13
POSITIVE LOGITS
taboo
0.28
shame
0.26
-tab
0.22
stigma
0.21
embarrassment
0.20
embarrassed
0.20
tab
0.20
Shame
0.19
ashamed
0.19
Topics
0.18
Activations Density 0.167%