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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rics
    -0.75
    otide
    -0.75
    acted
    -0.68
    ounty
    -0.67
    arty
    -0.67
    lance
    -0.66
    rums
    -0.65
    river
    -0.63
    ding
    -0.63
    iddler
    -0.63
    POSITIVE LOGITS
    chal
    1.09
    sel
    0.98
    chwitz
    0.97
    urance
    0.96
    pect
    0.95
    ques
    0.94
    sell
    0.94
    ocial
    0.94
    sembly
    0.91
    que
    0.91
    Act Density 0.102%

    No Known Activations