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

    Neuronpedia

    INDEX
    Explanations

    references to specific pages in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to specific pages in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CAST
    -0.76
    eca
    -0.67
    IUM
    -0.67
    ALLY
    -0.65
     Lauder
    -0.65
    oise
    -0.65
    ETH
    -0.63
    NetMessage
    -0.63
    EStreamFrame
    -0.58
     Jaw
    -0.58
    POSITIVE LOGITS
    antry
    1.55
    views
    1.22
    ants
    0.92
    pages
    0.91
    earance
    0.83
    render
    0.79
    Rank
    0.76
     layouts
    0.76
    cox
    0.76
    view
    0.75
    Act Density 0.028%

    No Known Activations