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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the special double underscore naming convention used in Python for private or special methods and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.80
    Pais
    -0.68
     Pais
    -0.66
    ).</
    -0.65
    BrowserModule
    -0.63
    Thor
    -0.62
     …)
    -0.60
    tle
    -0.60
     mati
    -0.59
     fre
    -0.58
    POSITIVE LOGITS
     __
    2.27
    (__
    2.04
     (__
    1.91
     (!__
    1.81
    ->__
    1.75
    .__
    1.71
     *__
    1.57
    )__
    1.56
    /__
    1.55
    __
    1.52
    Act Density 0.045%

    No Known Activations