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

    Neuronpedia

    INDEX
    Explanations

    reports of events or statements made by different individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of physical injury or harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nature
    -0.84
     abound
    -0.76
    DragonMagazine
    -0.74
     sorts
    -0.67
     Governments
    -0.66
     trillions
    -0.64
    imil
    -0.64
     EVENTS
    -0.63
    enment
    -0.62
    ptions
    -0.62
    POSITIVE LOGITS
     remarked
    0.91
     singled
    0.82
     commented
    0.77
     overheard
    0.77
     likened
    0.74
     summed
    0.74
    Said
    0.73
     joked
    0.73
     recounted
    0.71
     sarcast
    0.69
    Act Density 0.324%

    No Known Activations