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

    Neuronpedia

    INDEX
    Explanations

    phrases related to passwords

    oai_token-act-pair · gpt-3.5-turbo

    references to passwords in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.73
    rums
    -0.72
    nih
    -0.70
     Galile
    -0.70
    semble
    -0.69
    gaard
    -0.65
    iatus
    -0.64
    icles
    -0.64
    Ĥ¬
    -0.64
    ICLE
    -0.63
    POSITIVE LOGITS
     password
    1.14
     passwords
    1.13
    password
    0.96
     Password
    0.92
     authentication
    0.92
    Password
    0.91
     login
    0.90
     hashing
    0.89
     hashes
    0.88
     encryption
    0.87
    Act Density 0.021%

    No Known Activations