INDEX
Explanations
references to depression and its related phenomena
terms related to mental health conditions, specifically depression and suicidal thoughts
New Auto-Interp
Negative Logits
Sources
-0.86
SPONSORED
-0.84
seeing
-0.74
Reply
-0.74
lay
-0.71
leigh
-0.70
leon
-0.69
tnc
-0.69
quer
-0.68
aque
-0.67
POSITIVE LOGITS
depression
0.98
depressive
0.88
relapse
0.88
depress
0.77
symptoms
0.75
diagnosis
0.74
distress
0.73
relief
0.71
worsen
0.70
despair
0.70
Activations Density 0.019%