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

    Neuronpedia

    INDEX
    Explanations

    references to placeholder content and user registration prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     privilege
    -0.16
     Priv
    -0.16
     voks
    -0.15
    .Selenium
    -0.15
     McConnell
    -0.14
     privileges
    -0.14
    privileged
    -0.14
    Priv
    -0.14
    õ
    -0.14
    inge
    -0.14
    POSITIVE LOGITS
     Lal
    0.16
    uet
    0.16
    onom
    0.15
     bis
    0.15
     Cob
    0.15
    ãĥĻãĥ«
    0.15
    ella
    0.15
     ap
    0.14
    uyu
    0.14
     fel
    0.13
    Act Density 0.005%

    No Known Activations