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

    Neuronpedia

    INDEX
    Explanations

    password-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to passwords and account security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    66666666
    -0.75
    direct
    -0.72
    worldly
    -0.72
    cler
    -0.71
    nih
    -0.70
    obe
    -0.69
     Sheen
    -0.67
    Ĥ¬
    -0.66
    gaard
    -0.66
    rums
    -0.66
    POSITIVE LOGITS
     password
    1.31
     passwords
    1.28
     Password
    1.10
    Password
    1.07
    password
    1.02
     login
    0.94
     encryption
    0.85
     authentication
    0.84
     credentials
    0.84
     hashes
    0.84
    Act Density 0.009%

    No Known Activations