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

    Neuronpedia

    INDEX
    Explanations

    references to original works of art

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.19
    jab
    -0.15
    ilde
    -0.15
     Arch
    -0.15
    stru
    -0.14
     Karn
    -0.14
     happening
    -0.14
    spell
    -0.14
     Fare
    -0.14
     Stuart
    -0.14
    POSITIVE LOGITS
    аÑĢам
    0.17
    abbage
    0.16
    arily
    0.16
    eniz
    0.16
    agues
    0.15
    mmas
    0.15
    ivec
    0.15
    rawtypes
    0.14
    rokes
    0.14
    uitka
    0.14
    Act Density 0.023%

    No Known Activations