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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions or statements

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, likely a public figure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yield
    -0.75
     prolifer
    -0.72
     chained
    -0.71
     lawy
    -0.71
     weave
    -0.71
     leaps
    -0.70
     listing
    -0.68
     stakes
    -0.68
     partnerships
    -0.67
     uranium
    -0.66
    POSITIVE LOGITS
    ï¸ı
    1.38
    realDonaldTrump
    1.05
    kay
    1.00
    sic
    1.00
    Balt
    0.96
    20439
    0.94
    女
    0.93
    $
    0.92
    scar
    0.90
    esc
    0.90
    Act Density 0.202%

    No Known Activations