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

    Neuronpedia

    INDEX
    Explanations

    words related to destruction and damage

    oai_token-act-pair · gpt-3.5-turbo

    terms related to destruction and damage caused by disasters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Patent
    -0.85
     Teach
    -0.82
     patent
    -0.82
    sych
    -0.76
     veto
    -0.75
    Phys
    -0.73
     Freem
    -0.71
     precept
    -0.71
     patents
    -0.70
     monog
    -0.68
    POSITIVE LOGITS
    bris
    1.08
     debris
    0.92
     evacuated
    0.90
     makeshift
    0.87
    EMS
    0.87
     rubble
    0.80
     engulfed
    0.79
    د
    0.78
    affected
    0.76
     devastated
    0.76
    Act Density 0.274%

    No Known Activations