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

    Neuronpedia

    INDEX
    Explanations

    punctuations and specific sentence-ending formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENEFITS
    -0.78
    外部链接
    -0.78
    ynthia
    -0.74
     PopupWindow
    -0.74
    leſs
    -0.73
    itung
    -0.72
    empêcher
    -0.71
    IVERY
    -0.71
    igene
    -0.71
    waitKey
    -0.71
    POSITIVE LOGITS
    </i>
    0.65
    ↵
    0.65
    
    0.64
    .”
    0.64
    parsedMessage
    0.64
    </em>
    0.63
    ").
    0.59
    ))));
    0.59
    0.59
    .”)
    0.58
    Act Density 0.040%
    No Known Activations