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

    Neuronpedia

    INDEX
    Explanations

    references to individuals being killed in various types of incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to casualties or deaths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    caster
    -0.80
    Website
    -0.74
    $$$$
    -0.74
    ational
    -0.73
    CN
    -0.70
    Completed
    -0.70
    Registered
    -0.70
    Publisher
    -0.70
    ãĤ¹ãĥĪ
    -0.70
    Bey
    -0.70
    POSITIVE LOGITS
     infancy
    1.20
     childbirth
    1.16
     lieu
    0.98
     pursuit
    0.95
     relation
    0.93
     vain
    0.92
     captivity
    0.92
     accordance
    0.91
     situ
    0.90
     gunfire
    0.87
    Act Density 0.141%

    No Known Activations