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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cybersecurity and computer hacking

    oai_token-act-pair · gpt-3.5-turbo

    references to computer systems, hacking, and cybersecurity issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Grad
    -0.75
     Hunger
    -0.75
    ember
    -0.73
     Wrest
    -0.72
     Trib
    -0.70
    odder
    -0.68
     Trials
    -0.67
    iets
    -0.66
    ethe
    -0.65
    assic
    -0.64
    POSITIVE LOGITS
     passwords
    1.21
     encrypted
    1.15
     encryption
    1.13
     seized
    1.01
     password
    0.99
     devices
    0.98
     belonging
    0.97
     computers
    0.93
     encrypt
    0.92
     routers
    0.89
    Act Density 0.286%

    No Known Activations