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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals intertwined with potentially controversial or critical descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly in a critical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omy
    -0.75
    76561
    -0.72
    omaly
    -0.69
    OGR
    -0.69
    ogly
    -0.68
     Coverage
    -0.66
    ophy
    -0.66
    omal
    -0.66
    âĺ
    -0.64
    OA
    -0.62
    POSITIVE LOGITS
    sworth
    1.17
    intendent
    0.97
     Dunham
    0.83
    ston
    0.78
    entially
    0.78
    qua
    0.77
    staking
    0.75
    ritten
    0.73
    inary
    0.73
     Wildcats
    0.72
    Act Density 0.023%

    No Known Activations