INDEX
    Explanations

    mentions of the name "Cooper."

    New Auto-Interp
    Negative Logits
    chal
    -0.71
    enic
    -0.69
    rely
    -0.67
    eric
    -0.63
    untled
    -0.62
    facebook
    -0.60
     Blaz
    -0.58
     nerv
    -0.57
    seeing
    -0.57
    Magikarp
    -0.56
    POSITIVE LOGITS
     Cooper
    1.05
    stown
    0.99
    atives
    0.92
    icker
    0.88
     Draper
    0.87
    ately
    0.86
    agher
    0.82
    lear
    0.81
    ords
    0.80
    ature
    0.79
    Act Density 0.011%

    No Known Activations