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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data privacy and security issues

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals' personal data and privacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uph
    -0.77
    witz
    -0.73
    arcity
    -0.73
    aiman
    -0.69
    bender
    -0.69
    asant
    -0.68
    asus
    -0.68
    starter
    -0.67
    iculture
    -0.66
    cutting
    -0.65
    POSITIVE LOGITS
     passwords
    1.55
     data
    1.33
     emails
    1.29
     secrets
    1.28
     identities
    1.24
     information
    1.22
     records
    1.18
     password
    1.18
     files
    1.14
     Emails
    1.12
    Act Density 0.235%

    No Known Activations