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

    Neuronpedia

    INDEX
    Explanations

    hierarchically structured data or elements within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.62
     AssemblyCompany
    -0.62
    enterOuterAlt
    -0.50
    fillType
    -0.48
    complexContent
    -0.46
    <unused52>
    -0.45
     <>",
    -0.45
    pgterms
    -0.44
    TagNumber
    -0.44
    duma
    -0.44
    POSITIVE LOGITS
     tree
    0.83
     parent
    0.82
     father
    0.78
     subtree
    0.78
    tree
    0.75
     Tree
    0.75
    Tree
    0.74
     parents
    0.74
     child
    0.73
     recursively
    0.70
    Act Density 0.733%

    No Known Activations