INDEX
    Explanations

    references to female individuals and their origins or affiliations

    New Auto-Interp
    Negative Logits
    841
    -0.17
    enÃŃ
    -0.16
    uta
    -0.15
     Zem
    -0.15
     Economy
    -0.14
    abra
    -0.14
    ién
    -0.14
    udem
    -0.14
    orea
    -0.14
     cach
    -0.14
    POSITIVE LOGITS
    -gnu
    0.15
    -urlencoded
    0.15
    SWG
    0.14
    ELS
    0.14
    AAF
    0.14
    agara
    0.14
    ä»Ģ
    0.13
    禮
    0.13
    embed
    0.13
    skb
    0.13
    Act Density 0.009%

    No Known Activations