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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant events or actions involving large groups of people

    oai_token-act-pair · gpt-3.5-turbo

    commas and other punctuation marks that may indicate lists or separations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įåĸļ士
    -0.75
    abouts
    -0.71
    quished
    -0.69
    é¾į
    -0.68
    achev
    -0.66
    ajor
    -0.66
    oward
    -0.66
    Į
    -0.64
    iah
    -0.63
    £ı
    -0.63
    POSITIVE LOGITS
     apparel
    0.66
     nutrition
    0.65
    culture
    0.64
     including
    0.63
     livelihood
    0.63
     gore
    0.62
    communications
    0.61
     disabilities
    0.60
     ethnicity
    0.60
     minerals
    0.60
    Act Density 0.465%

    No Known Activations