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

    Neuronpedia

    INDEX
    Explanations

    terms related to internet privacy and surveillance

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to web browsing and internet surveillance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    herty
    -0.72
    Grad
    -0.71
     Wol
    -0.69
    icho
    -0.69
     tempered
    -0.67
     Undead
    -0.66
    Crew
    -0.66
    itsch
    -0.64
    ember
    -0.64
    reci
    -0.63
    POSITIVE LOGITS
     passwords
    1.24
     encrypted
    1.07
     malware
    0.98
     encryption
    0.96
     routers
    0.95
     metadata
    0.94
     computers
    0.94
     databases
    0.92
     networks
    0.92
     intercepted
    0.91
    Act Density 0.361%

    No Known Activations