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

    Neuronpedia

    INDEX
    Explanations

    references to passwords and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /**
    -0.72
     Tind
    -0.70
    ="#"><
    -0.68
    tifact
    -0.67
     useAppContext
    -0.66
    fisk
    -0.66
     Ami
    -0.66
    principalColumn
    -0.64
    lijken
    -0.63
    ")[
    -0.62
    POSITIVE LOGITS
     password
    2.48
     Password
    2.34
    password
    2.33
    Password
    2.24
     passwords
    2.11
    PASSWORD
    1.94
     PASSWORD
    1.72
    passwords
    1.62
    getPassword
    1.58
    Passwords
    1.53
    Act Density 0.046%

    No Known Activations