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

    Neuronpedia

    INDEX
    Explanations

    references to HTML elements and their attributes in a coded context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ("~/
    -0.90
    GraphicsUnit
    -0.84
     Chry
    -0.83
     Sopho
    -0.83
    ükemmel
    -0.82
     SRAM
    -0.80
     ſur
    -0.80
    edicated
    -0.80
     GenerationType
    -0.79
    cuses
    -0.79
    POSITIVE LOGITS
     element
    1.60
     elements
    1.58
    Element
    1.50
     Element
    1.46
     Elements
    1.45
     ELEMENT
    1.39
    element
    1.38
    Elements
    1.37
    elements
    1.32
    ELEMENT
    1.27
    Act Density 0.043%

    No Known Activations