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

    Neuronpedia

    INDEX
    Explanations

    references to cybersecurity threats and malware

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uber
    -0.16
    iloc
    -0.15
    _BOUNDS
    -0.15
    ignum
    -0.15
    vault
    -0.14
    typeparam
    -0.14
    phas
    -0.14
    kea
    -0.14
     bard
    -0.13
     Handy
    -0.13
    POSITIVE LOGITS
    linkplain
    0.16
     automat
    0.15
    ono
    0.15
    ÑĢÑĥÑĤ
    0.14
    è¿ij
    0.14
    YTE
    0.14
     unseen
    0.13
     exhaust
    0.13
    tol
    0.13
    walls
    0.13
    Act Density 0.010%

    No Known Activations