INDEX
    Explanations

    references to Planned Parenthood and related reproductive health services

    New Auto-Interp
    Negative Logits
     exh
    -0.17
     rám
    -0.15
     broad
    -0.15
    zen
    -0.15
     nar
    -0.15
    ei
    -0.15
    imler
    -0.14
    immer
    -0.13
    abinet
    -0.13
    rames
    -0.13
    POSITIVE LOGITS
    teg
    0.20
    zyst
    0.17
    ź
    0.16
    ,},↵
    0.15
    ustin
    0.14
    rikes
    0.14
    auga
    0.14
    alone
    0.14
    ãĥ¼ãĥĪ
    0.14
    peg
    0.14
    Act Density 0.004%

    No Known Activations