INDEX
    Explanations

    references to incarceration and the criminal justice system

    New Auto-Interp
    Negative Logits
    urally
    -0.16
     kiá»ĩn
    -0.15
    reff
    -0.15
    ÑģÑĤи
    -0.14
    elp
    -0.14
    oca
    -0.14
    hin
    -0.14
    fried
    -0.13
    ذÙĩ
    -0.13
     policing
    -0.13
    POSITIVE LOGITS
    iron
    0.17
     bars
    0.16
    house
    0.16
     camps
    0.16
    uitka
    0.16
    umba
    0.16
     cells
    0.16
    bound
    0.15
     LW
    0.15
    -cell
    0.15
    Act Density 0.028%

    No Known Activations