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

    Neuronpedia

    INDEX
    Explanations

    terms related to passwords and security

    oai_token-act-pair · gpt-3.5-turbo

    references to passwords and their various characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hower
    -0.78
    worldly
    -0.71
    rums
    -0.70
    obe
    -0.69
    66666666
    -0.68
    gaard
    -0.66
    nih
    -0.65
    cler
    -0.65
     Galile
    -0.64
    semble
    -0.64
    POSITIVE LOGITS
     password
    1.26
     passwords
    1.24
     Password
    1.08
    Password
    1.04
    password
    1.02
     login
    0.93
     captcha
    0.89
     encryption
    0.87
     authentication
    0.86
     hashes
    0.86
    Act Density 0.016%

    No Known Activations