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

    Neuronpedia

    INDEX
    Explanations

    phone numbers within text

    oai_token-act-pair · gpt-3.5-turbo

    instances of phone numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipation
    -0.83
    ulp
    -0.73
    minster
    -0.70
    herty
    -0.69
     contrace
    -0.69
    mble
    -0.69
    ersion
    -0.68
    raq
    -0.68
    reci
    -0.67
    ilib
    -0.66
    POSITIVE LOGITS
     passwords
    0.87
     identifier
    0.78
     password
    0.78
    plates
    0.75
     spoof
    0.75
     messenger
    0.74
     authentication
    0.74
     identification
    0.73
     cryptography
    0.72
    alogy
    0.72
    Act Density 0.082%

    No Known Activations