INDEX
    Explanations

    instances and variations of the word "baby."

    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.65
    <eos>
    -0.63
    conazole
    -0.61
    esgue
    -0.61
     CWE
    -0.60
     Klopp
    -0.59
     prior
    -0.57
     geprüft
    -0.57
    🥞
    -0.57
    -0.56
    POSITIVE LOGITS
     baby
    2.68
     Baby
    2.54
    Baby
    2.53
     babies
    2.50
    baby
    2.50
     BABY
    2.49
    BABY
    2.39
    babies
    2.12
     Babies
    2.09
     bébé
    1.98
    Act Density 0.037%

    No Known Activations