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

    Neuronpedia

    INDEX
    Explanations

    code or function-related keywords and attributes related to programming or data handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ëĦ¤ìĿ´íĬ¸
    -0.17
    ncoder
    -0.16
    utzer
    -0.15
    _IMPLEMENT
    -0.14
    sanitize
    -0.14
    imonial
    -0.14
    estroy
    -0.14
    alis
    -0.14
    Disposable
    -0.14
    inspace
    -0.14
    POSITIVE LOGITS
     treated
    0.27
     treat
    0.27
     Treat
    0.27
     ignored
    0.24
     ignores
    0.23
     treating
    0.23
     ignore
    0.23
     behand
    0.22
     treats
    0.22
    -treated
    0.22
    Act Density 0.275%

    No Known Activations