INDEX
    Explanations

    references to the word "Swift."

    mentions of the name "Taylor Swift."

    New Auto-Interp
    Negative Logits
    egal
    -0.77
    ãĥĩãĤ£
    -0.76
    irin
    -0.67
    ulhu
    -0.67
    abases
    -0.66
    代
    -0.65
    chell
    -0.65
    à©
    -0.63
     disappoint
    -0.63
    terior
    -0.62
    POSITIVE LOGITS
     Swift
    0.92
    omatic
    0.84
    ivari
    0.77
    ollen
    0.73
     Sparrow
    0.72
    itzer
    0.72
    itude
    0.71
    mann
    0.71
     Swim
    0.70
    ipe
    0.70
    Act Density 0.011%

    No Known Activations