INDEX
    Explanations

    references to clubs or club-related activities

    New Auto-Interp
    Negative Logits
    ously
    -0.18
    emachine
    -0.16
    prung
    -0.16
     trÃŃ
    -0.15
    JC
    -0.15
    castle
    -0.15
    all
    -0.15
    urous
    -0.14
    aylight
    -0.14
    cono
    -0.14
    POSITIVE LOGITS
    bing
    0.39
    bers
    0.35
    bable
    0.28
    bish
    0.27
    bed
    0.26
    ber
    0.25
    houses
    0.25
    bies
    0.23
    house
    0.22
    foot
    0.21
    Act Density 0.019%

    No Known Activations