INDEX
    Explanations

    small, common words

    New Auto-Interp
    Negative Logits
    prog
    -0.07
     christ
    -0.07
    )))
    ↵
    -0.06
    })"↵
    -0.06
     Regents
    -0.06
    ipt
    -0.06
    .fin
    -0.06
    _sessions
    -0.06
     Sanders
    -0.06
     chicks
    -0.06
    POSITIVE LOGITS
     viewController
    0.07
     pistol
    0.06
    .Popen
    0.06
     منابع
    0.06
     radioactive
    0.06
    _frm
    0.06
     soit
    0.06
    .setBorder
    0.06
     přibliž
    0.06
    respond
    0.06
    Act Density 0.016%

    No Known Activations