INDEX
    Explanations

    words related to mental health conditions, specifically focusing on depression

    mentions of depression and related mental health issues

    New Auto-Interp
    Negative Logits
    Reply
    -0.82
    Sources
    -0.81
    aque
    -0.74
    ateur
    -0.71
    umer
    -0.70
    SPONSORED
    -0.70
    lay
    -0.69
    ouver
    -0.68
    Grab
    -0.68
    leigh
    -0.67
    POSITIVE LOGITS
     relapse
    0.99
     depression
    0.91
     depressive
    0.86
     symptoms
    0.84
     diagnosis
    0.79
     disorder
    0.74
     worsen
    0.74
     medication
    0.73
     suff
    0.73
     Symptoms
    0.73
    Act Density 0.038%

    No Known Activations