INDEX
    Explanations

    specific names of individuals, particularly notable women

    New Auto-Interp
    Negative Logits
     Jr
    -0.17
     Brendan
    -0.14
    anst
    -0.14
    reb
    -0.14
    getInstance
    -0.13
    atÄĥ
    -0.13
    iasi
    -0.13
    ahy
    -0.13
    jerne
    -0.13
    olas
    -0.13
    POSITIVE LOGITS
     herself
    0.21
    /he
    0.18
    affer
    0.16
    ãģķãģĦ
    0.15
    éľ
    0.15
    plusplus
    0.14
    rient
    0.14
    athed
    0.14
    xfd
    0.14
    pector
    0.14
    Act Density 0.107%

    No Known Activations