INDEX
    Explanations

    mentions of the state of New York

    New Auto-Interp
    Negative Logits
    audiovisuel
    -0.79
    Бахар
    -0.77
     שוליים
    -0.70
     riuscito
    -0.70
     poveznice
    -0.66
    InjectAttribute
    -0.65
     disponibilités
    -0.65
     виправивши
    -0.63
     '\\;'
    -0.62
     biber
    -0.61
    POSITIVE LOGITS
     ny
    1.52
     NY
    1.35
     Ny
    1.34
    Ny
    1.24
    NY
    1.11
    ny
    1.02
     Nye
    0.87
    Nye
    0.84
    MMV
    0.81
    nyx
    0.80
    Act Density 0.036%

    No Known Activations