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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and structures in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ
    -0.17
    enza
    -0.15
    IVES
    -0.14
    CEPTION
    -0.14
    isser
    -0.14
    anger
    -0.14
    otch
    -0.14
     Nack
    -0.14
    gger
    -0.14
     even
    -0.14
    POSITIVE LOGITS
     Laud
    0.18
    à¥ģब
    0.17
    ruk
    0.15
    (())↵
    0.15
    ecast
    0.15
    ħ
    0.15
    erox
    0.14
    ű
    0.14
     Lor
    0.14
    ÛĢ
    0.14
    Act Density 0.004%

    No Known Activations