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

    Neuronpedia

    INDEX
    Explanations

    aspects of things or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to various components or features of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amaz
    -0.75
    anders
    -0.75
    ander
    -0.73
    gently
    -0.70
    odore
    -0.68
    prus
    -0.67
    ESCO
    -0.64
    claimed
    -0.63
    tails
    -0.63
    helm
    -0.63
    POSITIVE LOGITS
     thereof
    1.21
     of
    1.09
    ality
    0.88
    Of
    0.85
    ial
    0.85
    ials
    0.80
     aspects
    0.78
    hetical
    0.78
     Of
    0.77
    ially
    0.76
    Act Density 0.055%

    No Known Activations