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

    Neuronpedia

    INDEX
    Explanations

    code formatting and syntax elements in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eda
    -0.21
    edar
    -0.16
    nist
    -0.15
     Dah
    -0.15
    quit
    -0.14
    amet
    -0.14
     Cush
    -0.14
    .BLL
    -0.14
     Quit
    -0.13
    EDA
    -0.13
    POSITIVE LOGITS
    bash
    0.20
    `↵
    0.19
     bash
    0.18
     {.
    0.18
    diff
    0.17
    zens
    0.17
    ôt
    0.17
     shell
    0.15
    shell
    0.15
    umont
    0.15
    Act Density 0.005%

    No Known Activations