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

    Neuronpedia

    INDEX
    Explanations

    patterns and metrics related to performance in simulations or experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antt
    -0.17
    urent
    -0.14
    urr
    -0.14
    nee
    -0.14
    xffffffff
    -0.14
    uitar
    -0.13
     yazılım
    -0.13
    má
    -0.13
    Bond
    -0.13
    conn
    -0.13
    POSITIVE LOGITS
     Paula
    0.16
    ohana
    0.15
     nominal
    0.15
    (STD
    0.14
    erner
    0.14
    ktor
    0.14
    akan
    0.14
    ãĥ³ãĥ
    0.14
    ellen
    0.14
    peria
    0.13
    Act Density 0.904%

    No Known Activations