INDEX
    Explanations

    references to children and their experiences

    New Auto-Interp
    Negative Logits
    eer
    -0.17
    wy
    -0.16
    hem
    -0.16
    etri
    -0.16
    ors
    -0.15
    hm
    -0.15
    etak
    -0.15
    538
    -0.15
    atted
    -0.15
    ÄĻk
    -0.14
    POSITIVE LOGITS
    nap
    0.29
    ults
    0.21
     ages
    0.20
    friendly
    0.19
    -friendly
    0.18
     friendly
    0.18
    /ad
    0.17
    /people
    0.17
     aged
    0.17
    neys
    0.17
    Act Density 0.019%

    No Known Activations