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

    Neuronpedia

    INDEX
    Explanations

    references to elements in a scientific or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chry
    -0.81
    GraphicsUnit
    -0.80
    ("~/
    -0.80
     Sopho
    -0.80
    cuses
    -0.80
    pausal
    -0.79
     GenerationType
    -0.79
     ſur
    -0.79
    rugated
    -0.78
    ükemmel
    -0.77
    POSITIVE LOGITS
     elements
    1.43
     element
    1.41
     Elements
    1.34
    Element
    1.33
     Element
    1.30
    Elements
    1.26
     ELEMENT
    1.24
    IElement
    1.23
     ELEMENTS
    1.20
    ELEMENT
    1.19
    Act Density 0.038%

    No Known Activations