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

    Neuronpedia

    INDEX
    Explanations

    phrases related to violent incidents

    oai_token-act-pair · gpt-3.5-turbo

    mentions of shooting incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STEP
    -0.81
    hw
    -0.81
    Label
    -0.78
    ebook
    -0.77
    obo
    -0.76
    ateg
    -0.76
    ummies
    -0.74
    ulla
    -0.73
    GY
    -0.73
    undai
    -0.70
    POSITIVE LOGITS
     shooting
    1.21
     Shooting
    1.04
     spree
    1.02
     shoot
    1.01
     shootings
    0.96
     Shoot
    0.91
    nikov
    0.90
     shoots
    0.89
     shooters
    0.87
    powder
    0.86
    Act Density 0.012%

    No Known Activations