INDEX
    Explanations

    mentions of cows and cow-related terms

    references to cattle and related products

    New Auto-Interp
    Negative Logits
     Flavoring
    -0.90
     millenn
    -0.81
     satell
    -0.76
     Extend
    -0.75
    mble
    -0.74
    */(
    -0.68
     newsp
    -0.67
     Palestin
    -0.65
     overwhelming
    -0.65
     Fiction
    -0.65
    POSITIVE LOGITS
    boys
    1.32
    riter
    1.07
    ards
    1.05
     cows
    0.98
    girl
    0.94
    toe
    0.93
    yard
    0.91
    cake
    0.89
    girls
    0.86
    enne
    0.85
    Act Density 0.007%

    No Known Activations