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

    Neuronpedia

    INDEX
    Explanations

    commitments or promises made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bos
    -0.17
    _REQ
    -0.15
     reconc
    -0.14
    usch
    -0.14
    otas
    -0.13
    osaic
    -0.13
    iola
    -0.13
    едÑĮ
    -0.13
    ood
    -0.13
    ochen
    -0.13
    POSITIVE LOGITS
    ä¸įä¼ļ
    0.17
     commitment
    0.16
    aukee
    0.15
    aston
    0.15
    bsolute
    0.15
    committed
    0.15
     never
    0.15
    \Routing
    0.14
    ument
    0.14
     sẽ
    0.14
    Act Density 0.046%

    No Known Activations