INDEX
    Explanations

    mentions of the word "suit"

    words related to fashion or clothing

    New Auto-Interp
    Negative Logits
    mob
    -0.78
    olesc
    -0.74
     Citiz
    -0.65
    vez
    -0.65
     ultras
    -0.65
    480
    -0.64
    ILY
    -0.63
    bub
    -0.61
    appers
    -0.61
    μ
    -0.61
    POSITIVE LOGITS
    uit
    1.02
    eer
    1.00
    eers
    0.99
    eering
    0.85
    arist
    0.81
    ary
    0.76
    ously
    0.76
    inet
    0.75
    oise
    0.74
    rador
    0.73
    Act Density 0.014%

    No Known Activations