INDEX
    Explanations

    references to kidnapping and violence

    New Auto-Interp
    Negative Logits
     peace
    -0.17
    ATTER
    -0.15
    ohon
    -0.14
    amat
    -0.14
     match
    -0.14
    peace
    -0.14
    CHAN
    -0.14
     potential
    -0.14
     mutual
    -0.14
    turnstile
    -0.13
    POSITIVE LOGITS
    èµı
    0.16
    deo
    0.16
    icot
    0.15
    emand
    0.15
    eed
    0.15
    iar
    0.15
    ะà¹ģ
    0.14
     Gratuit
    0.14
    fee
    0.14
    bine
    0.14
    Act Density 0.177%

    No Known Activations