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

    Neuronpedia

    INDEX
    Explanations

    terms related to cybersecurity and security threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sg
    -0.17
    sl
    -0.16
    lets
    -0.16
    yers
    -0.16
    ikan
    -0.16
    sb
    -0.15
    sla
    -0.15
    кап
    -0.15
    idor
    -0.15
    sr
    -0.14
    POSITIVE LOGITS
    punk
    0.21
    0.16
    bul
    0.15
    liÄį
    0.15
    posium
    0.15
    Ark
    0.15
    é¾
    0.15
    Knife
    0.15
    security
    0.14
    chrome
    0.14
    Act Density 0.009%

    No Known Activations