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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to structural and architectural details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    219
    -0.14
    tin
    -0.14
    omid
    -0.13
    airs
    -0.13
     ore
    -0.13
    leigh
    -0.13
    gard
    -0.13
    quets
    -0.13
    rollo
    -0.13
     painting
    -0.12
    POSITIVE LOGITS
     components
    0.29
     elements
    0.28
    -elements
    0.27
    components
    0.25
    elements
    0.25
     segments
    0.23
    .elements
    0.23
     sections
    0.23
    /components
    0.23
    -components
    0.23
    Act Density 0.022%

    No Known Activations