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

    Neuronpedia

    INDEX
    Explanations

    references to guides and guides to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ities
    -0.19
    ITY
    -0.19
    ity
    -0.18
    ulu
    -0.17
    nen
    -0.17
    ns
    -0.16
    unts
    -0.16
    ses
    -0.16
    sov
    -0.16
    ally
    -0.16
    POSITIVE LOGITS
    book
    0.35
    posts
    0.28
    books
    0.27
    post
    0.23
    BOOK
    0.21
    ellar
    0.16
    -book
    0.16
    ance
    0.15
    .NewGuid
    0.15
    guide
    0.15
    Act Density 0.013%

    No Known Activations