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

    Neuronpedia

    INDEX
    Explanations

    fragments of code and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enko
    -0.17
     int
    -0.16
     struct
    -0.15
     Kim
    -0.15
     co
    -0.15
     var
    -0.15
     run
    -0.14
    hd
    -0.14
    kop
    -0.14
     gains
    -0.14
    POSITIVE LOGITS
     def
    0.20
    Ñİн
    0.15
    pike
    0.15
    anda
    0.15
    odef
    0.15
    	def
    0.14
    lasses
    0.14
    def
    0.14
     defe
    0.14
    άνÏĦα
    0.14
    Act Density 0.011%

    No Known Activations