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

    Neuronpedia

    INDEX
    Explanations

    patterns of parentheses, commas, and other punctuation marks commonly used in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eydi
    -0.17
    alchemy
    -0.16
    estroy
    -0.16
    HORT
    -0.15
     âĸ²
    -0.15
    çīĻ
    -0.15
    igits
    -0.15
    antha
    -0.14
    ancode
    -0.14
    anela
    -0.14
    POSITIVE LOGITS
     +
    0.23
     conc
    0.20
     Conc
    0.19
    ISTR
    0.17
    }${
    0.15
    تص
    0.14
    ’
    0.14
    istr
    0.14
    ões
    0.14
     perk
    0.14
    Act Density 0.050%

    No Known Activations