INDEX
    Explanations

    references to actions related to capital punishment or severe consequences

    New Auto-Interp
    Negative Logits
     Cruc
    -0.16
    ude
    -0.16
    submitted
    -0.15
     æľĿ
    -0.14
    öst
    -0.14
    .Builder
    -0.14
     Mour
    -0.14
     Schwarz
    -0.14
    ky
    -0.13
    uke
    -0.13
    POSITIVE LOGITS
    irut
    0.17
    .scalablytyped
    0.15
    tiv
    0.15
     Ñģид
    0.15
    ertas
    0.14
     Crowley
    0.14
    ihu
    0.13
     adulte
    0.13
    onas
    0.13
    áºŃu
    0.13
    Act Density 0.011%

    No Known Activations