INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     cleanly
    0.69
    normally
    0.66
     intermedia
    0.66
    sanity
    0.66
     тип
    0.65
    intera
    0.63
    cleanup
    0.61
     paper
    0.61
     પહો
    0.60
     Idam
    0.60
    POSITIVE LOGITS
     irresponsible
    0.67
     advocating
    0.66
     encourage
    0.65
     unethical
    0.65
     aventuras
    0.64
     advocated
    0.64
     Advocacy
    0.63
     probiotics
    0.63
     incroyable
    0.63
     suicidal
    0.62
    Act Density 0.000%

    No Known Activations