INDEX
    Explanations

    references to children's rights and protections

    New Auto-Interp
    Negative Logits
    agrid
    -0.17
    aight
    -0.17
    uke
    -0.16
    unta
    -0.15
     SY
    -0.15
     Admiral
    -0.14
    ORK
    -0.14
     tar
    -0.14
     split
    -0.14
     Preview
    -0.13
    POSITIVE LOGITS
     guaranteed
    0.25
     human
    0.24
     guarantee
    0.24
     rights
    0.24
     Rights
    0.23
     RIGHTS
    0.23
     guarantees
    0.22
    rights
    0.22
     Guar
    0.21
    Human
    0.21
    Act Density 0.113%

    No Known Activations