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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical actions in a chaotic or urgent setting

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of people and their actions in a chaotic or emergency situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Patent
    -0.71
     genius
    -0.65
     patent
    -0.65
     causation
    -0.65
     Ranking
    -0.64
     Inher
    -0.64
     XY
    -0.64
     monopoly
    -0.62
    Domain
    -0.62
     Disclosure
    -0.61
    POSITIVE LOGITS
     evacuated
    1.06
     makeshift
    1.06
     tents
    1.04
     belongings
    1.02
     disembark
    0.98
     balcon
    0.96
     evacuate
    0.96
     evacuation
    0.95
     stret
    0.95
     roofs
    0.95
    Act Density 0.862%

    No Known Activations