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

    Neuronpedia

    INDEX
    Explanations

    mentions of people's names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oho
    -0.92
    holes
    -0.89
    hole
    -0.88
    icals
    -0.85
    alez
    -0.85
    MpServer
    -0.83
    ache
    -0.78
    neys
    -0.77
    lon
    -0.75
    sea
    -0.73
    POSITIVE LOGITS
     Michele
    0.98
    afia
    0.87
     Giul
    0.74
     Vie
    0.73
     Sabb
    0.71
     Seym
    0.69
    aeda
    0.69
     Schmidt
    0.67
     Mü
    0.66
     Modest
    0.66
    Act Density 0.019%

    No Known Activations