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

    Neuronpedia

    INDEX
    Explanations

    references to keys used in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    al
    -0.17
    ationToken
    -0.16
    asure
    -0.16
    iate
    -0.15
    stal
    -0.14
    355
    -0.14
    mts
    -0.14
    alles
    -0.14
     heck
    -0.14
    apia
    -0.14
    POSITIVE LOGITS
    hole
    0.29
    chain
    0.26
    chains
    0.23
    ring
    0.23
    phrase
    0.22
    logger
    0.22
    cloak
    0.21
    notes
    0.21
    note
    0.21
    frames
    0.20
    Act Density 0.058%

    No Known Activations