INDEX
    Explanations

    terms related to the prison system and incarceration

    New Auto-Interp
    Negative Logits
     ado
    -0.16
    ulle
    -0.15
     gentlemen
    -0.15
    sik
    -0.15
    -eslint
    -0.15
    UDGE
    -0.14
    rim
    -0.14
     imprisonment
    -0.14
     prisons
    -0.14
    unched
    -0.14
    POSITIVE LOGITS
    ers
    0.28
    house
    0.23
     cells
    0.22
    /release
    0.22
     sentence
    0.21
    -cell
    0.20
     camps
    0.20
     sentences
    0.20
     camp
    0.20
     term
    0.20
    Act Density 0.030%

    No Known Activations