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

    Neuronpedia

    INDEX
    Explanations

    certain programming code syntax patterns, specifically those denoted by characters such as '>', '.', and '('

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks or specific characters in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lyn
    -0.73
    ohm
    -0.72
    iesel
    -0.70
    akuya
    -0.66
    kees
    -0.63
    izable
    -0.63
    mination
    -0.63
    selves
    -0.62
    abies
    -0.61
    mber
    -0.61
    POSITIVE LOGITS
    >(
    1.42
    hest
    0.75
     patiently
    0.68
    "},
    0.65
    paralle
    0.64
    Fact
    0.63
    anthrop
    0.63
    alia
    0.63
    SPONSORED
    0.63
     actionGroup
    0.62
    Act Density 0.003%

    No Known Activations