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

    Neuronpedia

    INDEX
    Explanations

    announcements or confirmations in text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating announcements or confirmations of news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.75
    milo
    -0.75
    inventoryQuantity
    -0.71
    imeters
    -0.66
    fen
    -0.66
    pes
    -0.65
    atech
    -0.65
    arse
    -0.65
     exting
    -0.64
    youtu
    -0.64
    POSITIVE LOGITS
     that
    1.22
    that
    1.07
     THAT
    0.91
     That
    0.63
     there
    0.56
     Alexa
    0.56
     NCT
    0.56
     Tiger
    0.55
     TEAM
    0.55
     tha
    0.54
    Act Density 0.293%

    No Known Activations