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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating competitive advantages or superiority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urve
    -0.15
    okes
    -0.15
    vette
    -0.14
    venes
    -0.14
    itta
    -0.14
     pie
    -0.14
    หมà¸Ķ
    -0.14
     odio
    -0.14
    spender
    -0.14
    isz
    -0.14
    POSITIVE LOGITS
    jet
    0.16
     advantage
    0.16
    uppen
    0.16
    pong
    0.15
    747
    0.14
     Advantage
    0.14
    chy
    0.14
     McGregor
    0.14
     mere
    0.14
     continental
    0.14
    Act Density 0.044%

    No Known Activations