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

    Neuronpedia

    INDEX
    Explanations

    phrases related to computer hacking

    oai_token-act-pair · gpt-3.5-turbo

    references to hacking and cybercrime activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Urban
    -0.75
    heny
    -0.73
    ois
    -0.73
    apest
    -0.73
    usk
    -0.72
    ilitarian
    -0.70
    issy
    -0.70
    itsch
    -0.68
     athlet
    -0.66
    ogie
    -0.66
    POSITIVE LOGITS
     passwords
    1.47
     encrypted
    1.43
     encryption
    1.42
     computers
    1.41
     servers
    1.39
     password
    1.37
     malware
    1.33
     routers
    1.31
     iCloud
    1.31
     encrypt
    1.28
    Act Density 0.722%

    No Known Activations