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

    Neuronpedia

    INDEX
    Explanations

    phrases related to security vulnerabilities and policy enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iversit
    -0.18
    agar
    -0.15
    麻
    -0.15
    ãĥ¼ãĥ«
    -0.14
    ÑĢÑĥд
    -0.14
     Rolling
    -0.14
    avra
    -0.14
    ault
    -0.14
    aroo
    -0.14
    åĨ
    -0.13
    POSITIVE LOGITS
     CVE
    0.16
    epar
    0.15
    processable
    0.15
    afd
    0.15
    iesel
    0.14
    ::_
    0.14
    atu
    0.13
     crafted
    0.13
    atro
    0.13
    (.)
    0.13
    Act Density 0.025%

    No Known Activations