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

    Neuronpedia

    INDEX
    Explanations

    references to summaries or overviews of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñģли
    -0.16
    zw
    -0.16
    ìĬ¹
    -0.15
    eft
    -0.15
    abyrin
    -0.14
    æĦı
    -0.14
    env
    -0.14
    uling
    -0.14
    adders
    -0.14
    親
    -0.14
    POSITIVE LOGITS
    ed
    0.23
    ing
    0.23
    stakes
    0.19
    led
    0.17
    hip
    0.15
    ../../../
    0.15
    gether
    0.15
    iá»ģn
    0.15
    -ÑĤо
    0.15
    rael
    0.15
    Act Density 0.016%

    No Known Activations