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

    Neuronpedia

    INDEX
    Explanations

    personal identifying information like names, hometowns, and email addresses

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of names and personal information details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iculture
    -0.77
    worms
    -0.76
    fires
    -0.71
    iven
    -0.67
    successfully
    -0.66
    Increases
    -0.66
    phas
    -0.65
    hig
    -0.65
    mud
    -0.64
    ievers
    -0.64
    POSITIVE LOGITS
     initials
    1.22
     surname
    1.22
     nationality
    1.19
     likeness
    1.08
     address
    1.06
     pronouns
    1.02
     Address
    1.00
     suffix
    0.99
     password
    0.98
     coordinates
    0.98
    Act Density 0.232%

    No Known Activations