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

    mentions of specific individuals, particularly Robert Webb

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.77
    ãĥĢ
    -0.73
    oras
    -0.71
    stood
    -0.70
    onym
    -0.69
    haps
    -0.69
    acerb
    -0.68
    pron
    -0.68
    CENT
    -0.66
    onyms
    -0.65
    POSITIVE LOGITS
     Webb
    1.20
     Dixon
    0.83
    owship
    0.79
    inson
    0.77
     Telescope
    0.76
    icz
    0.76
    yer
    0.76
     Hutch
    0.75
    swick
    0.73
    aba
    0.72
    Act Density 0.004%

    No Known Activations