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

    Neuronpedia

    INDEX
    Explanations

    news-related words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to news events or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.77
    orney
    -0.71
    asse
    -0.71
    amiya
    -0.67
    atos
    -0.67
    orsi
    -0.66
    ¯¯
    -0.66
    rylic
    -0.65
    inho
    -0.65
    ength
    -0.64
    POSITIVE LOGITS
    worthiness
    1.14
    worthy
    1.10
    flash
    1.03
    reader
    1.00
    room
    0.84
     announcement
    0.83
     announcements
    0.80
     headlines
    0.78
     RELEASE
    0.78
    print
    0.78
    Act Density 0.035%

    No Known Activations