INDEX
    Explanations

    references to the act of murder and related themes

    New Auto-Interp
    Negative Logits
    lage
    -0.19
    tle
    -0.16
    loha
    -0.15
    iÃŁ
    -0.14
    uplic
    -0.14
    oha
    -0.14
    ÑģÑĭлки
    -0.14
    arser
    -0.14
    rick
    -0.14
    tracted
    -0.14
    POSITIVE LOGITS
    ously
    0.18
    abilia
    0.17
    -su
    0.17
    isco
    0.16
    _skb
    0.16
    inch
    0.16
    uang
    0.16
    initely
    0.15
    ous
    0.15
    riers
    0.15
    Act Density 0.028%

    No Known Activations