INDEX
    Explanations

    questions about feeling or self-harm

    New Auto-Interp
    Negative Logits
     edgecolor
    0.46
    यू
    0.45
     yên
    0.42
     기업
    0.41
    认为
    0.40
     adorable
    0.40
     petite
    0.40
     fearless
    0.40
     backyard
    0.39
     napkin
    0.39
    POSITIVE LOGITS
     unjustly
    0.42
     unduly
    0.41
     stagn
    0.40
    ukul
    0.40
     Controlador
    0.40
    াইট
    0.39
    SplitContainer
    0.38
    Tanggal
    0.38
    0.38
    0.37
    Act Density 0.032%

    No Known Activations