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

    Neuronpedia

    INDEX
    Explanations

    characteristics of various string patterns and delimiters in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ose
    -0.17
    edy
    -0.16
    zk
    -0.16
    dub
    -0.15
    erv
    -0.14
    pac
    -0.14
    bris
    -0.14
    AME
    -0.14
    osa
    -0.14
    ̣
    -0.14
    POSITIVE LOGITS
    e
    0.18
    s
    0.18
    ÂĿ
    0.18
    es
    0.18
    ODULE
    0.15
    ган
    0.15
    sburg
    0.14
    enler
    0.14
    ogany
    0.14
    an
    0.14
    Act Density 0.059%

    No Known Activations