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

    Neuronpedia

    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    the name "Dean" across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.78
    atoon
    -0.78
    TOR
    -0.77
    enegger
    -0.75
     Flavoring
    -0.75
    roxy
    -0.71
    olitan
    -0.71
    psey
    -0.70
    iculty
    -0.69
    ickr
    -0.67
    POSITIVE LOGITS
     Winchester
    1.06
     Ambrose
    0.80
    uates
    0.75
    uate
    0.75
    plan
    0.72
     Foster
    0.72
    ysis
    0.70
     Beam
    0.70
    uation
    0.69
    ette
    0.69
    Act Density 0.019%

    No Known Activations