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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Dean" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TOR
    -0.79
    */(
    -0.63
    atoon
    -0.62
    nir
    -0.58
    artisan
    -0.57
    rious
    -0.56
     intersections
    -0.56
     paths
    -0.55
    enegger
    -0.55
     entrants
    -0.55
    POSITIVE LOGITS
     Winchester
    1.09
     Ambrose
    0.89
    owan
    0.85
    bolt
    0.79
    plan
    0.75
     Orn
    0.73
    ister
    0.73
    ette
    0.71
     Ba
    0.70
     Heller
    0.70
    Act Density 0.022%

    No Known Activations