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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting related to pagination or navigation within content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rag
    -0.15
    anes
    -0.15
    cedes
    -0.15
    roat
    -0.15
    rou
    -0.14
    rst
    -0.14
    sst
    -0.14
    fdc
    -0.14
     lesbi
    -0.14
    ARI
    -0.14
    POSITIVE LOGITS
    ÑĨов
    0.15
    ãĥĪãĥ«
    0.15
    ìĥģìľĦ
    0.15
    gettext
    0.14
    ropy
    0.14
    489
    0.14
    举
    0.14
    epy
    0.14
    657
    0.13
    twig
    0.13
    Act Density 0.001%

    No Known Activations