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

    Neuronpedia

    INDEX
    Explanations

    phrases related to violent events, specifically shootings

    oai_token-act-pair · gpt-3.5-turbo

    references to violent incidents, specifically shootings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GY
    -0.85
    undai
    -0.79
    ateg
    -0.77
    annis
    -0.74
    Label
    -0.73
    hw
    -0.73
    eday
    -0.73
    adian
    -0.72
    onge
    -0.72
    uchin
    -0.71
    POSITIVE LOGITS
     spree
    1.33
     rampage
    1.12
     deaths
    0.91
     shootings
    0.86
    nikov
    0.84
    powder
    0.80
     shooting
    0.80
     scenes
    0.79
     massacre
    0.79
     victims
    0.78
    Act Density 0.026%

    No Known Activations