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

    Neuronpedia

    INDEX
    Explanations

    references to passwords and login credentials

    oai_token-act-pair · gpt-3.5-turbo

    references to passwords and related security terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rums
    -0.72
    nih
    -0.70
    nian
    -0.67
    cler
    -0.67
    neau
    -0.67
     guiActiveUnfocused
    -0.66
    direct
    -0.66
    icles
    -0.65
    obe
    -0.65
    lander
    -0.64
    POSITIVE LOGITS
     password
    1.10
     passwords
    1.10
     hashes
    0.95
     Password
    0.94
     authentication
    0.93
    password
    0.91
     login
    0.91
     captcha
    0.88
     hashing
    0.87
    Password
    0.87
    Act Density 0.029%

    No Known Activations