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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific entities or concepts, focusing on terms related to legal matters, medical conditions or geographical places

    oai_token-act-pair · gpt-3.5-turbo

    specific demographic or statistical references related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Investor
    -0.67
    arthy
    -0.65
    ebook
    -0.63
     Carnegie
    -0.62
     Faith
    -0.62
    esi
    -0.61
    uddin
    -0.61
    RAW
    -0.60
    gov
    -0.60
     Betsy
    -0.59
    POSITIVE LOGITS
    votes
    0.88
    keyes
    0.81
    imore
    0.71
    phies
    0.65
    iliated
    0.64
     apiece
    0.64
     singles
    0.64
    secut
    0.63
     bonded
    0.63
     strugg
    0.62
    Act Density 0.354%

    No Known Activations