INDEX
    Explanations

    references to New York and its associated entities

    New Auto-Interp
    Negative Logits
    iform
    -0.17
    ittel
    -0.16
    nar
    -0.16
    /co
    -0.14
    itel
    -0.14
    ednou
    -0.14
    ucci
    -0.14
    orte
    -0.13
     Dün
    -0.13
    adding
    -0.13
    POSITIVE LOGITS
     City
    0.46
    City
    0.36
     CITY
    0.35
     city
    0.30
    city
    0.25
    -city
    0.24
    _city
    0.22
    /New
    0.21
     State
    0.21
    å¸Ĥ
    0.21
    Act Density 0.033%

    No Known Activations