INDEX
Explanations
mentions of mental health conditions and their associated symptoms
New Auto-Interp
Negative Logits
Roskov
-0.82
DockStyle
-0.61
oa̍t
-0.56
adaptiveStyles
-0.56
alve
-0.53
WriteTagHelper
-0.52
PostInfinity
-0.51
quillo
-0.51
instr
-0.50
Maxi
-0.50
POSITIVE LOGITS
depression
1.00
Depression
0.98
Depression
0.96
antidepress
0.96
depressive
0.96
Bipolar
0.93
bipolar
0.91
depression
0.90
Psychiatry
0.87
psychiatry
0.86
Activations Density 0.327%