INDEX
    Explanations

    the word "cub" in various contexts

    references to "cubs" or "cub" in various contexts

    New Auto-Interp
    Negative Logits
    ++++
    -0.84
    ++++++++++++++++
    -0.71
     Ack
    -0.67
    ARP
    -0.65
    wine
    -0.64
    Downloadha
    -0.64
    lessly
    -0.63
     Hath
    -0.62
     Heck
    -0.62
    OWER
    -0.61
    POSITIVE LOGITS
    icle
    1.26
    icles
    1.17
    ility
    1.06
    ensis
    0.95
    bies
    0.93
    emen
    0.91
    ilings
    0.90
    ilant
    0.90
    raph
    0.90
    bage
    0.90
    Act Density 0.056%

    No Known Activations