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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific symbols and formatting in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bum
    -0.17
    urst
    -0.16
     Architects
    -0.16
    -await
    -0.15
    achment
    -0.15
    oder
    -0.14
    anus
    -0.14
    icken
    -0.14
     Conway
    -0.14
     Archives
    -0.14
    POSITIVE LOGITS
     def
    0.36
    	def
    0.31
    class
    0.26
     class
    0.24
    def
    0.24
    if
    0.23
     Def
    0.17
    iforn
    0.17
    -def
    0.16
    (class
    0.16
    Act Density 0.006%

    No Known Activations