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 fatal violence or death

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soType
    -0.90
    MpServer
    -0.89
    Avg
    -0.83
    ECA
    -0.80
    Catalog
    -0.79
    Clar
    -0.76
    MN
    -0.74
    Brew
    -0.73
    Limited
    -0.73
     CLIENT
    -0.73
    POSITIVE LOGITS
    blow
    0.87
    adder
    0.82
    ously
    0.81
    stroke
    0.79
    face
    0.79
    claw
    0.78
    anguage
    0.78
     psychiat
    0.75
    guard
    0.74
     retard
    0.73
    Act Density 0.024%

    No Known Activations