INDEX
    Explanations

    phrases related to social media marketing and user engagement

    New Auto-Interp
    Negative Logits
    pek
    -0.15
    üml
    -0.15
    ustos
    -0.15
    ucch
    -0.15
    loat
    -0.15
    ãĤ¡
    -0.15
    GuidId
    -0.15
    оÑĢод
    -0.14
    à¸Ľà¸£à¸°à¸Īำ
    -0.14
    amilies
    -0.14
    POSITIVE LOGITS
     Fake
    0.20
     fake
    0.20
    100
    0.16
    Fake
    0.16
     Paid
    0.15
    abant
    0.15
     faker
    0.15
     Artificial
    0.15
     paid
    0.14
    fake
    0.14
    Act Density 0.019%

    No Known Activations