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

    Neuronpedia

    INDEX
    Explanations

    words related to negative outcomes or consequences

    oai_token-act-pair · gpt-3.5-turbo

    key themes of popular culture, particularly related to the Hunger Games series and concepts of social dynamics like "herd mentality" and being "spoiled."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyomi
    -1.03
    ially
    -0.92
    etheless
    -0.83
    itars
    -0.79
    sembly
    -0.79
     occas
    -0.77
    igel
    -0.75
    psey
    -0.74
    cknow
    -0.73
    iate
    -0.73
    POSITIVE LOGITS
    Redd
    0.85
    é¾
    0.79
     Animals
    0.77
    Animal
    0.73
    ACY
    0.71
    Trend
    0.70
    Thumbnail
    0.70
    Wild
    0.69
     chickens
    0.69
    Stop
    0.69
    Act Density 0.059%

    No Known Activations