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

    Neuronpedia

    INDEX
    Explanations

    commands and declarations of authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ropoda
    -0.16
    ossip
    -0.14
     Middle
    -0.14
    eneg
    -0.14
    нÑĤ
    -0.14
    arent
    -0.13
    ader
    -0.13
    ç½²
    -0.13
    issen
    -0.13
    mage
    -0.13
    POSITIVE LOGITS
    icus
    0.15
    ishi
    0.15
    éģĵ
    0.14
    ermann
    0.13
    CLU
    0.13
    éħ¸
    0.13
    IGIN
    0.13
     Smarty
    0.13
     Eigen
    0.13
     Soup
    0.13
    Act Density 0.137%

    No Known Activations