INDEX
    Explanations

    references to abortion and related issues

    New Auto-Interp
    Negative Logits
    ertino
    -0.19
    oggler
    -0.18
    olo
    -0.17
    ussen
    -0.16
    LEGRO
    -0.15
    legen
    -0.14
     sublic
    -0.14
    YZ
    -0.14
    åħ¸
    -0.14
    rror
    -0.14
    POSITIVE LOGITS
    akis
    0.16
    paging
    0.15
    icket
    0.14
    mium
    0.14
    akah
    0.14
    awah
    0.13
    reh
    0.13
    spin
    0.13
     Birch
    0.13
    еÑİ
    0.13
    Act Density 0.275%

    No Known Activations