INDEX
    Explanations

    images or mentions of cats, especially kittens

    references to cats and kittens

    New Auto-Interp
    Negative Logits
    unda
    -0.84
     Petroleum
    -0.76
    eous
    -0.74
    ioxide
    -0.69
     GOODMAN
    -0.68
     Sachs
    -0.68
    indal
    -0.66
    nce
    -0.65
    ijn
    -0.63
    states
    -0.63
    POSITIVE LOGITS
     kittens
    1.01
     paws
    1.00
     kitten
    0.97
     pets
    0.96
     paw
    0.92
     puppies
    0.91
     euth
    0.86
     zoo
    0.86
     cats
    0.86
     grooming
    0.84
    Act Density 0.068%

    No Known Activations