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

    Neuronpedia

    INDEX
    Explanations

    the structure of explanations that start with "how."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .webkit
    -0.18
    eways
    -0.14
    POOL
    -0.14
    /xhtml
    -0.14
    imson
    -0.14
    azio
    -0.14
    tiv
    -0.14
    има
    -0.14
     Globe
    -0.14
    ureau
    -0.14
    POSITIVE LOGITS
    acho
    0.14
    ακ
    0.14
    /oct
    0.14
    nost
    0.14
    Ĩ
    0.14
    unami
    0.14
     Berm
    0.14
    _exempt
    0.14
    anh
    0.14
    ани
    0.13
    Act Density 0.017%

    No Known Activations