INDEX
    Explanations

    words or phrases related to judicial punishment or violence

    references to execution and related events or concepts

    New Auto-Interp
    Negative Logits
    ijn
    -0.85
    asio
    -0.72
    thora
    -0.71
    inki
    -0.71
    ï¸ı
    -0.70
    IGH
    -0.68
    é¾įåĸļ士
    -0.67
    é¾įå
    -0.66
    ĨĴ
    -0.65
    UTH
    -0.65
    POSITIVE LOGITS
     executions
    0.91
     execution
    0.84
    locks
    0.81
    eering
    0.78
     inmate
    0.78
     executed
    0.77
     execute
    0.76
    icts
    0.75
     executes
    0.73
     convict
    0.73
    Act Density 0.058%

    No Known Activations