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

    Neuronpedia

    INDEX
    Explanations

    references to malware and cybersecurity threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     HACK
    -0.17
     safety
    -0.14
     Hack
    -0.14
    .Designer
    -0.14
    inh
    -0.14
    bis
    -0.14
    ugu
    -0.14
     Datensch
    -0.14
    openid
    -0.14
     bis
    -0.14
    POSITIVE LOGITS
     campaigns
    0.24
     actor
    0.23
     campaign
    0.23
    Campaign
    0.22
    campaign
    0.22
     actors
    0.22
     Campaign
    0.21
     Actors
    0.19
    _campaign
    0.19
     dro
    0.19
    Act Density 0.206%

    No Known Activations