INDEX
    Explanations

    geographical locations and names, particularly related to New York City

    New Auto-Interp
    Negative Logits
     useContext
    -0.60
     zirconium
    -0.60
     Obispo
    -0.57
    posedge
    -0.57
     nakalista
    -0.53
    RequestMapping
    -0.52
    nocache
    -0.51
    -0.50
     Euphrates
    -0.50
    ixar
    -0.49
    POSITIVE LOGITS
     NYC
    1.25
    NYC
    1.17
     Brooklyn
    1.01
     Bronx
    1.00
     Manhattan
    1.00
     Amsterdam
    0.96
     Toronto
    0.96
    nyc
    0.94
     Mumbai
    0.94
    Mumbai
    0.91
    Act Density 0.907%

    No Known Activations