INDEX
    Explanations

    mentions of free food promotions or offers

    New Auto-Interp
    Negative Logits
    anka
    -0.15
    agna
    -0.15
    ÙıÙĨ
    -0.14
    arken
    -0.14
    otton
    -0.14
    099
    -0.14
    isel
    -0.14
    кÑĢа
    -0.13
    klä
    -0.13
    dea
    -0.13
    POSITIVE LOGITS
    oyer
    0.16
     handjob
    0.13
    IDO
    0.13
     Yield
    0.13
    653
    0.13
     processing
    0.13
     intox
    0.13
     Processing
    0.13
     thu
    0.13
     browsing
    0.12
    Act Density 0.173%

    No Known Activations