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

    Neuronpedia

    INDEX
    Explanations

    words related to news and events

    oai_token-act-pair · gpt-3.5-turbo

    references to news events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orney
    -0.78
    BuyableInstoreAndOnline
    -0.72
    ause
    -0.65
    ignt
    -0.65
    alties
    -0.64
    volent
    -0.62
    inho
    -0.61
    ength
    -0.61
     habitable
    -0.61
     quir
    -0.60
    POSITIVE LOGITS
    worthy
    1.15
    flash
    1.14
    worthiness
    1.06
    reader
    1.02
    room
    0.92
    rooms
    0.92
    week
    0.90
     headlines
    0.89
    print
    0.87
     outlets
    0.87
    Act Density 0.034%

    No Known Activations