INDEX
    Explanations

    mentions of the word "ginger" or related terms

    New Auto-Interp
    Negative Logits
    ategory
    -0.79
    zzi
    -0.76
    ĵĺ
    -0.70
    igslist
    -0.67
    illon
    -0.66
    rior
    -0.65
     Shelby
    -0.65
    iries
    -0.65
     compan
    -0.64
    respond
    -0.63
    POSITIVE LOGITS
    bread
    1.62
    glass
    0.96
    bats
    0.88
    prise
    0.84
    lich
    0.83
    mond
    0.78
    laus
    0.77
    lings
    0.76
    bang
    0.76
    hoff
    0.74
    Act Density 0.025%

    No Known Activations