INDEX
    Explanations

    terms related to execution and capital punishment

    New Auto-Interp
    Negative Logits
    282
    -0.15
    çek
    -0.15
    asan
    -0.14
    repos
    -0.14
    531
    -0.14
     Impress
    -0.14
     èĮ
    -0.14
    woo
    -0.14
    illow
    -0.13
    eÄį
    -0.13
    POSITIVE LOGITS
    ixa
    0.17
    ubb
    0.15
    мм
    0.15
    emand
    0.14
    /classes
    0.14
    êm
    0.14
     побаÑĩ
    0.14
    loat
    0.14
    rys
    0.13
    acious
    0.13
    Act Density 0.011%

    No Known Activations