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

    Neuronpedia

    INDEX
    Explanations

    references to specific programming elements and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uate
    -0.17
    á»ĵi
    -0.16
    anto
    -0.16
    ichten
    -0.16
    antha
    -0.15
    	Copyright
    -0.15
    Äĩ
    -0.14
    jo
    -0.14
    Æ°Æ¡i
    -0.14
    ints
    -0.14
    POSITIVE LOGITS
     Slee
    0.17
    -du
    0.15
     vá»įng
    0.15
     Papers
    0.14
     larg
    0.14
    oga
    0.14
    rog
    0.14
     Aust
    0.14
     Rog
    0.13
     Punch
    0.13
    Act Density 0.002%

    No Known Activations