INDEX
    Explanations

    references to activities or items related to children

    repeated references to children or kids

    New Auto-Interp
    Negative Logits
    uncture
    -0.71
     subsequ
    -0.71
    asca
    -0.71
     manifold
    -0.69
     freight
    -0.67
     incorporation
    -0.66
    uner
    -0.65
    ihara
    -0.64
     conditional
    -0.60
     deposition
    -0.60
    POSITIVE LOGITS
    kids
    0.93
    girl
    0.90
     Doodle
    0.89
    ults
    0.89
    olor
    0.87
    boys
    0.84
     kids
    0.83
    bowl
    0.80
    glers
    0.80
     boys
    0.79
    Act Density 0.022%

    No Known Activations