INDEX
    Explanations

    references to the city of Atlanta

    occurrences of the word "Atlanta."

    New Auto-Interp
    Negative Logits
    VALUE
    -0.79
    gger
    -0.72
    onies
    -0.72
    cess
    -0.69
    byn
    -0.69
    uddin
    -0.68
    zanne
    -0.65
     facult
    -0.65
    lda
    -0.65
    orical
    -0.65
    POSITIVE LOGITS
     Braves
    1.12
     Falcons
    1.10
     Atlanta
    0.95
     Hawks
    0.89
     skyline
    0.84
    Atlanta
    0.82
    iens
    0.80
     Wire
    0.74
     Bulldogs
    0.73
     Prototype
    0.71
    Act Density 0.005%

    No Known Activations