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

    Neuronpedia

    INDEX
    Explanations

    references to the Library of Congress and associated institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.18
    loff
    -0.17
    345
    -0.16
    icans
    -0.15
    roys
    -0.15
    327
    -0.14
    ift
    -0.14
    ãĤ¯ãĥ©ãĥĸ
    -0.14
    _cast
    -0.14
    atrice
    -0.14
    POSITIVE LOGITS
    illing
    0.17
    imoto
    0.15
    adian
    0.15
    sel
    0.14
     å·
    0.14
    ZN
    0.14
     Newman
    0.13
    inea
    0.13
    urai
    0.13
    atform
    0.13
    Act Density 0.002%

    No Known Activations