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

    Neuronpedia

    INDEX
    Explanations

    punctuation-related cues and sentence structure in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eca
    -0.15
    sit
    -0.15
     kh
    -0.15
    elder
    -0.14
    (Have
    -0.14
    rott
    -0.14
    jsonp
    -0.13
    ilogy
    -0.13
    513
    -0.13
    syscall
    -0.13
    POSITIVE LOGITS
     ë°Ķë¡ľ
    0.16
    artment
    0.15
    CREMENT
    0.14
    iare
    0.13
    imientos
    0.13
     Gale
    0.13
    udder
    0.13
    ugg
    0.13
    ewise
    0.13
    _OS
    0.13
    Act Density 0.214%

    No Known Activations