INDEX
    Explanations

    geographical references related to New York City and its surrounding areas

    New Auto-Interp
    Negative Logits
    ushman
    -0.18
    anova
    -0.17
    hw
    -0.17
    unker
    -0.16
    ears
    -0.14
     asc
    -0.14
    Scaler
    -0.14
    meni
    -0.14
    .sd
    -0.14
    upe
    -0.14
    POSITIVE LOGITS
    TT
    0.14
     Сов
    0.14
    imus
    0.13
    bindung
    0.13
    andel
    0.13
    nia
    0.13
    aba
    0.13
    dik
    0.13
    wer
    0.13
    GIN
    0.13
    Act Density 0.014%

    No Known Activations