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

    Neuronpedia

    INDEX
    Explanations

    numeric values and certain specific tokens in code-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avenport
    -0.16
     Singleton
    -0.14
    werp
    -0.13
    allet
    -0.13
     committed
    -0.13
     Morton
    -0.13
    ulo
    -0.13
    Ĺ
    -0.13
    emer
    -0.13
    Singleton
    -0.12
    POSITIVE LOGITS
    orgia
    0.15
    anian
    0.13
    ÅĽci
    0.13
    /owl
    0.13
    zyst
    0.13
    ãĤ
    0.13
    æĭŁ
    0.13
     ãģı
    0.13
    .Alpha
    0.13
    bury
    0.12
    Act Density 0.071%

    No Known Activations