INDEX
    Explanations

    phrases related to promotional events and giveaways

    New Auto-Interp
    Negative Logits
    abella
    -0.16
    #ga
    -0.16
    bens
    -0.16
    eldo
    -0.15
    ellas
    -0.15
    lej
    -0.15
    occo
    -0.15
    STALL
    -0.15
    lesc
    -0.14
    лÑĥги
    -0.14
    POSITIVE LOGITS
    /free
    0.15
    jee
    0.14
    reason
    0.14
    _NOTICE
    0.14
    ué
    0.13
     ward
    0.13
    yas
    0.13
     Vir
    0.13
    istrict
    0.13
     alternating
    0.13
    Act Density 0.005%

    No Known Activations