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

    Neuronpedia

    INDEX
    Explanations

    structured data formats and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the beginning of a sentence or document (denoted by <bos>).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    the beginning of a sequence or document, specifically marked by `<bos>`.

    oai_token-act-pair · gpt-4oTriggered by @neilrathi
    New Auto-Interp
    Negative Logits
    AddHtmlAttribute
    -0.50
    .*")]
    -0.50
    RenderAtEndOf
    -0.47
     Speicher
    -0.43
     Sosial
    -0.43
    دانشنامهٔ
    -0.43
     bēr
    -0.42
     AssemblyTitle
    -0.41
     prohibido
    -0.41
     schließlich
    -0.41
    POSITIVE LOGITS
    ValueStyle
    0.71
     esternos
    0.64
    :+:
    0.63
    Chham
    0.57
    Билгалдахарш
    0.57
    Искәрмәләр
    0.54
     Taktlose
    0.54
    مقاله
    0.54
    FunctionFlags
    0.53
     ब्रेकडाउन
    0.51
    Act Density 0.911%

    No Known Activations