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

    Neuronpedia

    INDEX
    Explanations

    various types of parentheses and brackets in code or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bris
    -0.15
    bben
    -0.15
    TRACE
    -0.14
    uben
    -0.14
    illet
    -0.13
    itz
    -0.13
    /repos
    -0.13
    abox
    -0.13
     æł
    -0.13
    arta
    -0.13
    POSITIVE LOGITS
    IFS
    0.17
    eniz
    0.15
    rend
    0.15
    alama
    0.14
    ickers
    0.14
    âĸį
    0.14
     neutral
    0.14
    alink
    0.14
    Versions
    0.14
    azine
    0.14
    Act Density 0.184%

    No Known Activations