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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and their relationships or roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Twe
    -0.17
    arn
    -0.15
    iper
    -0.14
    osition
    -0.14
    etsk
    -0.14
    erli
    -0.14
    iki
    -0.14
    ัวà¸Ńย
    -0.14
     Anyone
    -0.14
    irim
    -0.14
    POSITIVE LOGITS
    æĿ¥è¯´
    0.27
    è¿Ļæĺ¯
    0.22
     sake
    0.16
    ,this
    0.15
    ÑĪло
    0.15
    >this
    0.14
    enal
    0.14
     ÑįÑĤо
    0.14
    #${
    0.14
     ÑĨе
    0.14
    Act Density 0.066%

    No Known Activations