INDEX
    Explanations

    expressions of emotional struggle and societal responsibilities

    New Auto-Interp
    Negative Logits
     knull
    -0.15
    iaux
    -0.15
    inker
    -0.15
    _Callback
    -0.14
    rophe
    -0.14
    orrow
    -0.14
    ADS
    -0.14
     unnecessarily
    -0.14
     Corner
    -0.13
    ozo
    -0.13
    POSITIVE LOGITS
     brush
    0.43
     ignore
    0.41
    brush
    0.39
     brushes
    0.37
     brushed
    0.37
     brushing
    0.37
     gloss
    0.36
     Brush
    0.35
    ignore
    0.35
    -ignore
    0.35
    Act Density 0.332%

    No Known Activations