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

    Neuronpedia

    INDEX
    Explanations

    references to passwords or related security terms

    oai_token-act-pair · gpt-3.5-turbo

    references to passwords and password-related security concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rums
    -0.87
    icles
    -0.77
     Fathers
    -0.73
     Galile
    -0.69
    icle
    -0.67
     Yards
    -0.66
    semble
    -0.64
     Spirits
    -0.64
    ICLE
    -0.64
    lander
    -0.63
    POSITIVE LOGITS
     password
    1.24
     passwords
    1.20
     Password
    1.12
     login
    1.10
     captcha
    1.10
    password
    1.07
    Password
    1.03
     authentication
    1.03
     hashes
    1.00
     username
    0.95
    Act Density 0.035%

    No Known Activations