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

    Neuronpedia

    INDEX
    Explanations

    news articles or reports about deadly incidents or casualties

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals who have been killed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcsstore
    -1.04
    hist
    -0.87
     stru
    -0.81
    soDeliveryDate
    -0.75
    channelAvailability
    -0.74
    soType
    -0.74
    æ©Ł
    -0.73
    DragonMagazine
    -0.72
    Han
    -0.71
    yrinth
    -0.68
    POSITIVE LOGITS
     spree
    0.94
     gunshot
    0.84
     rampage
    0.79
    bolt
    0.78
     Trayvon
    0.78
     Sandra
    0.75
     psychiat
    0.75
    hyde
    0.74
     indict
    0.70
     stabbing
    0.70
    Act Density 0.100%

    No Known Activations