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

    Neuronpedia

    INDEX
    Explanations

    fill-in-the-blank sentences or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HAM
    -0.16
    ookie
    -0.16
    emark
    -0.15
     toll
    -0.14
    tica
    -0.14
    SES
    -0.14
     cet
    -0.14
    jac
    -0.14
    stick
    -0.14
    haar
    -0.14
    POSITIVE LOGITS
     Barry
    0.15
    é¡į
    0.15
    yz
    0.15
    \Tests
    0.14
    czy
    0.14
    ysize
    0.13
    )=='
    0.13
    à¥ĥ
    0.13
     Oaks
    0.13
     ÐĿаз
    0.13
    Act Density 0.004%

    No Known Activations