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

    Neuronpedia

    INDEX
    Explanations

    social media handles and Twitter usernames

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lisbon
    -0.73
     tape
    -0.71
     lipstick
    -0.71
     Borders
    -0.69
     Bran
    -0.69
     cholesterol
    -0.67
     Pyramid
    -0.65
     Corinth
    -0.65
     wards
    -0.65
     Bradford
    -0.65
    POSITIVE LOGITS
    realDonaldTrump
    0.96
    uers
    0.92
    Sports
    0.92
    ANI
    0.92
    groups
    0.92
    hash
    0.89
    news
    0.87
    Know
    0.87
    nat
    0.87
    thereal
    0.87
    Act Density 0.064%

    No Known Activations