INDEX
    Explanations

    groups of people

    New Auto-Interp
    Negative Logits
    izzie
    -0.07
    -0.06
     send
    -0.06
     mbox
    -0.06
     Round
    -0.06
    Silver
    -0.06
    /value
    -0.06
    ory
    -0.06
     드라마
    -0.06
    >I
    -0.06
    POSITIVE LOGITS
     eapply
    0.07
    します
    0.07
     были
    0.06
     derec
    0.06
     Unexpected
    0.06
     стать
    0.06
    áfico
    0.06
    ्ठ
    0.06
    COORD
    0.06
    _ylabel
    0.06
    Act Density 0.052%

    No Known Activations