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

    Neuronpedia

    INDEX
    Explanations

    reports of violent incidents resulting in casualties

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     disclaimer
    -0.78
    inventoryQuantity
    -0.78
     caveat
    -0.78
    soDeliveryDate
    -0.73
    Wide
    -0.70
    flush
    -0.68
     vetoed
    -0.68
     motto
    -0.67
     aster
    -0.65
    soType
    -0.64
    POSITIVE LOGITS
     innocent
    1.17
     civilians
    0.97
     pedestrians
    0.96
     innoc
    0.96
     bystanders
    0.91
     people
    0.83
     unarmed
    0.80
     occupants
    0.80
     souls
    0.78
     unsuspecting
    0.78
    Act Density 0.103%

    No Known Activations