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

    Neuronpedia

    INDEX
    Explanations

    phone numbers, addresses, and other identification numbers in the text

    oai_token-act-pair · gpt-3.5-turbo

    identifiers, particularly numbers associated with personal information such as license plates and phone numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reci
    -0.82
    kus
    -0.73
    issance
    -0.72
    ossom
    -0.71
    lux
    -0.71
    EMENT
    -0.70
    ulp
    -0.70
    romeda
    -0.69
    ittle
    -0.69
    assic
    -0.68
    POSITIVE LOGITS
    plates
    0.92
     redacted
    0.91
     spoof
    0.86
     dial
    0.82
     anonym
    0.79
     Aadhaar
    0.78
     passwords
    0.78
     aliases
    0.78
     "@
    0.77
     lookup
    0.77
    Act Density 0.122%

    No Known Activations