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

    Neuronpedia

    INDEX
    Explanations

    keywords related to governance, oversight, and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kee
    -0.17
     Mosque
    -0.16
    igor
    -0.16
    igo
    -0.15
    #
    -0.15
    ismet
    -0.14
    hai
    -0.14
    ë²Į
    -0.14
    cka
    -0.14
     Garland
    -0.14
    POSITIVE LOGITS
    awy
    0.19
    lej
    0.18
    .ps
    0.17
     ÙĢ
    0.16
    ÙĪ
    0.16
     Shall
    0.15
     Fou
    0.15
    Та
    0.15
     Haw
    0.15
     hint
    0.15
    Act Density 0.532%

    No Known Activations