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
    Sound
    -0.75
    ract
    -0.74
    STRUCT
    -0.74
     McDonnell
    -0.72
    ajor
    -0.71
    ocal
    -0.70
     Instruction
    -0.69
     Advent
    -0.68
    ModLoader
    -0.67
    Interstitial
    -0.67
    POSITIVE LOGITS
     passwords
    1.10
     password
    0.98
     inappropriately
    0.91
     breaches
    0.89
     belonging
    0.83
     offline
    0.82
     unlawfully
    0.82
     deletion
    0.81
     breach
    0.78
     encryption
    0.77
    Act Density 0.062%

    No Known Activations