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

    Neuronpedia

    INDEX
    Explanations

    references to examples and implementations in a technical or instructional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĻ
    -0.16
    aux
    -0.15
    appable
    -0.15
    agit
    -0.14
    anca
    -0.13
     Dumpster
    -0.13
    edith
    -0.13
    iece
    -0.13
    inning
    -0.13
    .cp
    -0.13
    POSITIVE LOGITS
     example
    0.44
    example
    0.34
     Example
    0.33
    ä¾ĭ
    0.33
     examples
    0.32
    Example
    0.32
     exemple
    0.31
     ejemplo
    0.29
    /example
    0.28
     exemplo
    0.28
    Act Density 0.057%

    No Known Activations