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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers or citations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    )))));
    -0.52
     Comb
    -0.51
     surla
    -0.49
     Ew
    -0.48
     Wink
    -0.48
    ])]
    -0.48
    Handlung
    -0.47
     Havre
    -0.47
    walt
    -0.47
    kup
    -0.47
    POSITIVE LOGITS
     ویکی‌پدی
    0.80
     ujednoznacz
    0.69
    Personensuche
    0.66
     Créez
    0.66
    Напомним
    0.64
    सन्दर्भ
    0.63
     للاسماء
    0.62
     doInBackground
    0.60
     مؤرشف
    0.59
    tagHelperRunner
    0.59
    Act Density 0.017%

    No Known Activations