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

    Neuronpedia

    INDEX
    Explanations

    prompts or instructions asking users to enter specific information or commands

    oai_token-act-pair · gpt-3.5-turbo

    instructions or prompts for user input in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arers
    -0.68
    ettes
    -0.62
    çİĭ
    -0.61
    Reilly
    -0.61
    plement
    -0.61
     Dal
    -0.60
    andal
    -0.59
    rior
    -0.58
     millenn
    -0.58
    ¥µ
    -0.58
    POSITIVE LOGITS
     captcha
    1.22
     passwords
    1.02
     username
    0.96
     Password
    0.94
     keywords
    0.93
     password
    0.89
     coordinates
    0.89
     "%
    0.88
     credentials
    0.88
     your
    0.86
    Act Density 0.091%

    No Known Activations