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

    Neuronpedia

    INDEX
    Explanations

    mentions of chemical weapons

    oai_token-act-pair · gpt-3.5-turbo

    references to chemical weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     4090
    -0.87
    shire
    -0.80
     Vander
    -0.78
    alos
    -0.77
     Wilde
    -0.77
     Hood
    -0.76
    stretched
    -0.76
    abouts
    -0.73
    doms
    -0.72
    inoa
    -0.71
    POSITIVE LOGITS
     chemical
    1.09
     makeup
    0.99
     warfare
    0.98
     compounds
    0.90
     chemicals
    0.89
     bombings
    0.89
     chlorine
    0.89
     weapons
    0.88
     munitions
    0.86
     substances
    0.86
    Act Density 0.012%

    No Known Activations