INDEX
    Explanations

    references to ages or the concept of being "years old."

    New Auto-Interp
    Negative Logits
    ooth
    -0.18
    linky
    -0.15
    zone
    -0.15
    hud
    -0.14
    MBER
    -0.14
    vla
    -0.14
    же
    -0.14
    cion
    -0.14
    óż
    -0.14
    880
    -0.14
    POSITIVE LOGITS
    yo
    0.19
     tuá»ķi
    0.16
    ½
    0.16
    akter
    0.15
    â̳
    0.15
    ÅĻev
    0.15
    UNC
    0.13
    th
    0.13
    DOB
    0.13
    yro
    0.13
    Act Density 0.037%

    No Known Activations