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

    Neuronpedia

    INDEX
    Explanations

    mentions of explosive devices or situations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of explosives or explosive-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cedented
    -0.87
    aird
    -0.83
    SEA
    -0.79
    pai
    -0.79
    alian
    -0.77
    heit
    -0.76
    alth
    -0.76
    esan
    -0.76
    atche
    -0.76
    beard
    -0.73
    POSITIVE LOGITS
     explosive
    0.98
     eru
    0.96
     decomp
    0.86
     incendiary
    0.84
     deton
    0.75
     disposal
    0.74
     flares
    0.74
     darts
    0.74
     propulsion
    0.72
    endiary
    0.72
    Act Density 0.017%

    No Known Activations