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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of importance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekler
    -0.17
    orado
    -0.15
     Narc
    -0.15
    tridge
    -0.15
    adu
    -0.14
    rello
    -0.14
    fty
    -0.14
    ekl
    -0.14
    ify
    -0.14
    ietf
    -0.14
    POSITIVE LOGITS
    æݪ
    0.16
    agna
    0.15
    ìķ¡
    0.15
     Já
    0.14
    è¡¡
    0.14
    elson
    0.14
    /lists
    0.14
    zá
    0.13
    /dev
    0.13
    pread
    0.13
    Act Density 0.099%

    No Known Activations