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

    Neuronpedia

    INDEX
    Explanations

    terms related to malicious cyber activities and threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢÑı
    -0.17
    Unsafe
    -0.16
     resc
    -0.16
     traj
    -0.15
     Unsafe
    -0.15
     Jungle
    -0.15
    ulkan
    -0.15
     synthes
    -0.14
    omial
    -0.14
    yan
    -0.14
    POSITIVE LOGITS
     cyber
    0.24
     hacking
    0.23
     interference
    0.21
     cy
    0.21
     hack
    0.21
     cybersecurity
    0.20
     Cyber
    0.20
     hackers
    0.19
    cy
    0.19
     targeting
    0.19
    Act Density 0.082%

    No Known Activations