INDEX
    Explanations

    mentions of various mayors' names

    New Auto-Interp
    Negative Logits
     instruments
    -0.67
    dates
    -0.66
    opter
    -0.65
    aeda
    -0.65
    reen
    -0.65
     Reincarnated
    -0.64
    ...]
    -0.62
     notebooks
    -0.62
    gettable
    -0.60
    othal
    -0.59
    POSITIVE LOGITS
    alty
    1.55
    alties
    1.06
     mayoral
    0.98
     borough
    0.96
    Mayor
    0.96
     mayor
    0.93
     Mayor
    0.92
     councillor
    0.89
     oun
    0.86
     Blasio
    0.84
    Act Density 0.054%

    No Known Activations