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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with data points or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rrggbb
    -1.04
    contentLoaded
    -0.97
    ########.
    -0.91
    XmlAccessorType
    -0.89
    sizeCache
    -0.88
    出版年
    -0.88
    Tikang
    -0.87
     חיצוניים
    -0.87
    DockStyle
    -0.87
     "..\..\..\
    -0.86
    POSITIVE LOGITS
     الحره
    0.65
    *
    0.46
    ره
    0.45
    ś
    0.44
    ctomy
    0.44
     comédie
    0.43
     completo
    0.42
    how
    0.40
     complètes
    0.40
     Zweig
    0.40
    Act Density 0.150%

    No Known Activations