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

    Neuronpedia

    INDEX
    Explanations

    terms related to policy, governance, and advisory roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     repmat
    -0.15
     اÙĦÙĤرÙĨ
    -0.15
     bast
    -0.14
    æµľ
    -0.14
    (s
    -0.14
     виб
    -0.14
    onse
    -0.13
    имоÑģÑĤÑĮ
    -0.13
     dock
    -0.13
    ocab
    -0.13
    POSITIVE LOGITS
    YL
    0.18
    lü
    0.16
    leton
    0.15
    à¸ģระ
    0.15
    arov
    0.15
    yl
    0.14
     Há»Ļi
    0.14
    _initializer
    0.14
    zcze
    0.14
    ãĥ£
    0.14
    Act Density 0.034%

    No Known Activations