INDEX
    Explanations

    references to birds and wildlife

    New Auto-Interp
    Negative Logits
    isbn
    -0.17
    lates
    -0.15
    ithe
    -0.15
    aurus
    -0.14
    alf
    -0.14
    abad
    -0.14
    oui
    -0.14
    imers
    -0.14
    eway
    -0.14
    NullOr
    -0.14
    POSITIVE LOGITS
    -wing
    0.17
     Wings
    0.17
     wings
    0.16
     drying
    0.15
     wing
    0.15
    sey
    0.15
    azon
    0.15
    że
    0.15
    wing
    0.14
    é³¥
    0.14
    Act Density 0.060%

    No Known Activations