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

    Neuronpedia

    INDEX
    Explanations

    references to prior information or points previously mentioned

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    558
    -0.15
    ÑĨÑĸ
    -0.14
    stown
    -0.14
    556
    -0.14
     appropriate
    -0.14
    ahas
    -0.14
    559
    -0.14
    ÏĦαÏĤ
    -0.14
    ÃĹ↵↵
    -0.14
    ist
    -0.13
    POSITIVE LOGITS
    -described
    0.18
    asan
    0.17
    /current
    0.17
    edList
    0.17
    utura
    0.15
    eniable
    0.14
    aub
    0.14
    ersiz
    0.14
    curity
    0.14
    above
    0.14
    Act Density 0.024%

    No Known Activations