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

    Neuronpedia

    INDEX
    Explanations

    technological processes or tools involving specific tasks or components

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to scientific processes and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bernatorial
    -0.88
    nai
    -0.71
    utenberg
    -0.70
    ghazi
    -0.68
    agate
    -0.62
     Klux
    -0.61
    essage
    -0.61
     Subway
    -0.60
    icipated
    -0.58
     tallest
    -0.58
    POSITIVE LOGITS
    .''
    0.71
     overseen
    0.69
    .''.
    0.69
    eers
    0.68
    _.
    0.66
    .</
    0.65
    .[
    0.64
     designed
    0.63
    .}
    0.63
     supplemented
    0.63
    Act Density 0.428%

    No Known Activations