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

    Neuronpedia

    INDEX
    Explanations

    terms related to cyber attacks and vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usu
    -0.16
    ead
    -0.16
    quier
    -0.16
    üt
    -0.15
     Bart
    -0.15
    loff
    -0.15
    isia
    -0.14
     Decomp
    -0.14
    /LICENSE
    -0.14
    iew
    -0.14
    POSITIVE LOGITS
    èŃľ
    0.15
    837
    0.15
    yš
    0.14
    CLS
    0.14
     U
    0.14
     ενÏĮÏĤ
    0.13
    æĭĽ
    0.13
    bach
    0.13
     susceptibility
    0.13
     weaker
    0.13
    Act Density 0.065%

    No Known Activations