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

    Neuronpedia

    INDEX
    Explanations

    average values or quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical averages or mean values in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocaly
    -0.66
    sure
    -0.61
    ariat
    -0.59
    mare
    -0.59
    special
    -0.58
     Others
    -0.58
     skelet
    -0.58
    otech
    -0.57
    eton
    -0.57
    lez
    -0.56
    POSITIVE LOGITS
    serving
    0.79
    unda
    0.66
     hourly
    0.63
     yearly
    0.62
    cens
    0.61
    netflix
    0.61
     82
    0.60
    awi
    0.59
    ucket
    0.59
     epis
    0.58
    Act Density 0.033%

    No Known Activations