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

    Neuronpedia

    INDEX
    Explanations

    proper names related to people

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals, particularly those associated with specific events or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \/\/
    -0.84
    女
    -0.83
    dinand
    -0.78
    orpor
    -0.72
    astics
    -0.70
    reated
    -0.70
    reatment
    -0.70
    eenth
    -0.69
    ugal
    -0.69
    spr
    -0.68
    POSITIVE LOGITS
     Conrad
    0.95
    aults
    0.86
     Cummings
    0.69
     Mai
    0.69
     Codex
    0.68
     Rogers
    0.67
    vier
    0.66
    ian
    0.66
     Akin
    0.66
     Orig
    0.65
    Act Density 0.011%

    No Known Activations