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

    Neuronpedia

    INDEX
    Explanations

    information related to violent events like attacks, bombings, shootings, and casualties

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    issance
    -0.70
    sonian
    -0.66
     Advertisement
    -0.65
     Unless
    -0.64
    inventoryQuantity
    -0.58
     Awakens
    -0.57
     mund
    -0.57
     semantics
    -0.57
    essor
    -0.56
     Dating
    -0.56
    POSITIVE LOGITS
    athi
    0.80
     flown
    0.73
     injured
    0.71
     already
    0.70
     killed
    0.68
     hospitalized
    0.67
     crammed
    0.67
     reportedly
    0.67
    involved
    0.66
     enrolled
    0.66
    Act Density 11.404%

    No Known Activations