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

    Neuronpedia

    INDEX
    Explanations

    personal and sensitive information

    oai_token-act-pair · gpt-3.5-turbo

    references to personal and sensitive information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ajor
    -0.73
    STRUCT
    -0.73
    Leader
    -0.72
    ocal
    -0.71
    unct
    -0.71
     Advent
    -0.68
    Sound
    -0.67
     benches
    -0.67
    ido
    -0.66
    ModLoader
    -0.65
    POSITIVE LOGITS
     passwords
    0.96
     inappropriately
    0.94
     password
    0.90
     breaches
    0.87
     privacy
    0.82
     unlawfully
    0.82
     encrypted
    0.81
     collected
    0.78
     belonging
    0.78
     leakage
    0.77
    Act Density 0.074%

    No Known Activations