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

    Neuronpedia

    INDEX
    Explanations

    keywords related to technology and computer programming

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names related to entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.99
    anwhile
    -0.93
     pione
    -0.91
    Þ
    -0.90
     conclud
    -0.85
     referen
    -0.83
    Ý
    -0.82
    ß
    -0.78
     teasp
    -0.77
    ñ
    -0.77
    POSITIVE LOGITS
    astery
    0.91
    usters
    0.87
    istries
    0.86
    omaly
    0.85
    etry
    0.82
    ioxide
    0.81
    itaire
    0.80
    rage
    0.79
    stice
    0.79
    ribune
    0.77
    Act Density 0.143%

    No Known Activations