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

    Neuronpedia

    INDEX
    Explanations

    references to violent actions resulting in death

    oai_token-act-pair · gpt-3.5-turbo

    references to death or fatality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soType
    -0.92
    MpServer
    -0.76
    Clar
    -0.76
    Null
    -0.75
    MN
    -0.74
    quickShipAvailable
    -0.73
    ī
    -0.72
     Compliance
    -0.71
    Catalog
    -0.70
    soDeliveryDate
    -0.68
    POSITIVE LOGITS
    ously
    0.85
    anguage
    0.85
    arcer
    0.77
    ishly
    0.75
    face
    0.74
    locked
    0.72
     starvation
    0.72
    hound
    0.71
     violently
    0.70
    oor
    0.70
    Act Density 0.038%

    No Known Activations