INDEX
    Explanations

    references to babies and baby-related products

    New Auto-Interp
    Negative Logits
    lei
    -0.19
    elig
    -0.14
    ammen
    -0.14
     past
    -0.14
    sto
    -0.14
    edis
    -0.14
    çݲ
    -0.14
    lej
    -0.14
    ibel
    -0.14
    ath
    -0.14
    POSITIVE LOGITS
    hood
    0.22
    Wunused
    0.17
    zers
    0.16
    -boy
    0.15
    atform
    0.15
    ppt
    0.14
     Byl
    0.14
    kins
    0.14
    arters
    0.14
    arsed
    0.14
    Act Density 0.012%

    No Known Activations