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

    Neuronpedia

    INDEX
    Explanations

    information related to death and injuries in conflicts

    oai_token-act-pair · gpt-3.5-turbo

    statements about fatalities and injuries resulting from violence or accidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.71
    wcsstore
    -0.69
     drawer
    -0.65
     answ
    -0.64
     disclaimer
    -0.62
    ilege
    -0.61
     Advice
    -0.60
     Purpose
    -0.59
     caveat
    -0.59
    DIS
    -0.58
    POSITIVE LOGITS
     apiece
    0.89
     casualties
    0.83
     fatalities
    0.82
     deaths
    0.79
    abouts
    0.79
     worldwide
    0.73
    iami
    0.72
     overdoses
    0.72
     bystanders
    0.71
    ributes
    0.71
    Act Density 0.104%

    No Known Activations