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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers or reports, particularly those related to arXiv submissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.56
    temp
    -0.54
    */
    -0.49
    ne
    -0.49
     contigo
    -0.48
    se
    -0.48
    -
    -0.47
    by
    -0.47
    kript
    -0.47
    te
    -0.46
    POSITIVE LOGITS
     Савезне
    0.97
    بوابة
    0.93
    Datuak
    0.84
     Majefty
    0.82
     للاسماء
    0.82
    Portale
    0.80
    Personensuche
    0.80
     cherchés
    0.79
     bezeichneter
    0.79
     متعلقه
    0.78
    Act Density 0.026%

    No Known Activations