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

    Neuronpedia

    INDEX
    Explanations

    references to decision-making processes and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uncan
    -0.15
    ernet
    -0.15
    FFE
    -0.15
    ICA
    -0.14
     Vend
    -0.14
    ahu
    -0.14
     Dun
    -0.13
    pte
    -0.13
     bis
    -0.13
    egr
    -0.13
    POSITIVE LOGITS
     etc
    0.22
    /**↵↵
    0.15
     ÑĤоÑīо
    0.15
    æĻ´
    0.14
     Chim
    0.14
    pute
    0.14
    ümÃ¼ÅŁ
    0.14
    ussian
    0.13
    ouri
    0.13
     ë°¤
    0.13
    Act Density 0.142%

    No Known Activations