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

    Neuronpedia

    INDEX
    Explanations

    descriptions of violent incidents or crimes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    200000
    -0.95
    soDeliveryDate
    -0.93
    Companies
    -0.86
    CHR
    -0.82
    ROM
    -0.82
    DragonMagazine
    -0.82
    hered
    -0.80
    DIT
    -0.79
    NESS
    -0.78
    Iss
    -0.78
    POSITIVE LOGITS
     gunfire
    1.27
     unarmed
    1.13
     gunshot
    1.05
     rampage
    1.03
     gunshots
    1.02
     explosion
    0.95
     wounding
    0.95
     shootout
    0.95
     injuring
    0.94
     spree
    0.93
    Act Density 14.640%

    No Known Activations