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

    Neuronpedia

    INDEX
    Explanations

    social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media applications and platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hol
    -0.69
    baugh
    -0.65
     traverse
    -0.63
    cled
    -0.63
    EStreamFrame
    -0.62
     regress
    -0.62
     induct
    -0.61
     mill
    -0.61
    toe
    -0.61
    bda
    -0.60
    POSITIVE LOGITS
     Privacy
    0.97
    Secure
    0.87
     Telegram
    0.80
     Pinterest
    0.80
     Security
    0.77
     Hots
    0.73
    Activity
    0.71
     Email
    0.71
    Talk
    0.71
     Messenger
    0.71
    Act Density 0.019%

    No Known Activations