Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to fitness, particularly in the context of activities like CrossFit training

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "fit" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mub
    -0.76
     tomat
    -0.68
    wcs
    -0.68
    etheless
    -0.67
    perty
    -0.67
    ammy
    -0.66
    icious
    -0.64
     carrot
    -0.63
    kefeller
    -0.63
     unanswered
    -0.62
    POSITIVE LOGITS
    ters
    1.14
    fitting
    1.07
    fit
    1.06
    gerald
    0.95
    MENTS
    0.93
     Fit
    0.88
    Fit
    0.88
    ments
    0.88
    fits
    0.85
     Trainer
    0.82
    Act Density 0.012%

    No Known Activations