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

    Neuronpedia

    INDEX
    Explanations

    references to social justice and accountability issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    款
    -0.14
    éĻIJå®ļ
    -0.14
    ilecek
    -0.14
    ãĥ«ãĤ¯
    -0.14
    ëĭĿ
    -0.13
    ohon
    -0.13
    ç±
    -0.13
    _:*
    -0.13
    /by
    -0.13
    atical
    -0.13
    POSITIVE LOGITS
     themselves
    0.22
    ekk
    0.16
    893
    0.15
    peria
    0.15
     Recogn
    0.14
    odia
    0.14
    ForKey
    0.14
     us
    0.14
    enberg
    0.14
     Monk
    0.14
    Act Density 0.659%

    No Known Activations