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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies or publications

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

    scientific or academic citation details, like author names, publication years, and journal references.

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

    The presence of scientific terminology and references, indicating formal academic or technical writing.

    eleuther_acts_top20 · gpt-4o-miniTriggered by @neilrathi

    scientific references and citations, such as author names, journal names, and publication details.

    oai_token-act-pair · gpt-4oTriggered by @neilrathi
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.73
    OGND
    -0.72
     שוליים
    -0.59
     blurry
    -0.58
    tanleria
    -0.57
     exhale
    -0.56
     emojis
    -0.56
     noDo
    -0.56
     selfies
    -0.56
    stonia
    -0.55
    POSITIVE LOGITS
    FieldNumber
    0.41
    昭和
    0.33
     Soviet
    0.32
     gewä
    0.31
    DIPSETTING
    0.31
    DropTable
    0.30
     USSR
    0.28
    Soviet
    0.28
     radio
    0.27
     recherches
    0.27
    Act Density 0.701%

    No Known Activations