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

    Neuronpedia

    INDEX
    Explanations

    references to hacking and cybersecurity incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Walsh
    -0.14
    HASH
    -0.14
    aires
    -0.14
    ares
    -0.14
    oodoo
    -0.14
     kiá»ĩn
    -0.14
    ebi
    -0.13
     gim
    -0.13
    -bed
    -0.13
    rase
    -0.13
    POSITIVE LOGITS
    ceph
    0.15
    ishly
    0.14
    paces
    0.14
    illez
    0.14
    eries
    0.13
    uffman
    0.13
    erson
    0.13
     Peek
    0.13
    /conf
    0.13
    771
    0.13
    Act Density 0.028%

    No Known Activations