INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    alance
    -0.08
     proletariat
    -0.08
    _calc
    -0.07
    total
    -0.07
    _launch
    -0.07
    기로
    -0.06
     incomplete
    -0.06
     Tone
    -0.06
    -0.06
    -0.06
    POSITIVE LOGITS
     Bush
    0.21
     bush
    0.20
    Bush
    0.18
     bushes
    0.15
    ush
    0.12
     Mos
    0.09
    USH
    0.09
    osh
    0.08
    issue
    0.08
     Biden
    0.08
    Act Density 0.003%

    No Known Activations