INDEX
    Explanations

    requests for audience engagement or actions

    New Auto-Interp
    Negative Logits
    èİİ
    -0.15
    :&
    -0.15
     Raphael
    -0.14
     Lob
    -0.14
    olen
    -0.14
     Mess
    -0.13
    wal
    -0.13
     ve
    -0.13
     Heard
    -0.13
    openhagen
    -0.13
    POSITIVE LOGITS
     maz
    0.15
    eddar
    0.14
    erli
    0.13
    ëıĦ를
    0.13
     Wich
    0.13
    arma
    0.13
     ÑĢÑĸд
    0.13
    /comments
    0.13
    ulant
    0.13
    νοÏħ
    0.13
    Act Density 0.113%

    No Known Activations