INDEX
    Explanations

    violent/sexual activity

    New Auto-Interp
    Negative Logits
    pixel
    -0.07
     Hor
    -0.07
    _equiv
    -0.07
     disciplines
    -0.06
     hypers
    -0.06
    Hor
    -0.06
    _pick
    -0.06
    _pins
    -0.06
    .putString
    -0.06
     Eternal
    -0.06
    POSITIVE LOGITS
     jedem
    0.07
     shoved
    0.06
    iedy
    0.06
    ahrungen
    0.06
    _Action
    0.06
    Recommend
    0.06
    (ErrorMessage
    0.06
     كرد
    0.06
     фундамент
    0.06
     pushed
    0.06
    Act Density 0.012%

    No Known Activations