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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific events or actions involving people

    oai_token-act-pair · gpt-3.5-turbo

    references to protests or incidents involving injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nature
    -0.80
    DragonMagazine
    -0.80
     abound
    -0.66
    imil
    -0.58
     Governments
    -0.58
     groundwork
    -0.58
    actionDate
    -0.58
    ptions
    -0.57
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.57
    channelAvailability
    -0.56
    POSITIVE LOGITS
     remarked
    1.02
     overheard
    0.94
     singled
    0.89
     joked
    0.88
     commented
    0.87
     recounts
    0.86
     reportedly
    0.85
     recounted
    0.85
     summed
    0.84
     likened
    0.84
    Act Density 0.234%

    No Known Activations