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

    Neuronpedia

    INDEX
    Explanations

    incidents of physical harm and injuries

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -1.14
     bandwagon
    -0.85
    eworld
    -0.77
     schedules
    -0.76
    MQ
    -0.75
     fleets
    -0.73
     quotas
    -0.72
    stakes
    -0.71
    lease
    -0.68
    ezvous
    -0.68
    POSITIVE LOGITS
     bruises
    1.38
     injuries
    1.30
     wounds
    1.28
     bruising
    1.25
     amput
    1.21
     fractures
    1.16
    rapnel
    1.16
     bruised
    1.15
     swollen
    1.14
     gunshot
    1.11
    Act Density 0.272%

    No Known Activations