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

    Neuronpedia

    INDEX
    Explanations

    references to valuable items or concepts, particularly those that suggest rarity or high worth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agn
    -0.17
    _requires
    -0.15
    go
    -0.15
    zial
    -0.14
    eo
    -0.14
    ForResult
    -0.14
    sembly
    -0.14
    cono
    -0.14
    \<^
    -0.14
    eco
    -0.13
    POSITIVE LOGITS
    èĪ¬
    0.15
    baum
    0.14
    &s
    0.14
    ieber
    0.14
    coil
    0.14
    ilde
    0.14
    SPA
    0.14
    hest
    0.14
    mond
    0.14
    utzer
    0.13
    Act Density 0.037%

    No Known Activations