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

    Neuronpedia

    INDEX
    Explanations

    references related to the public, society, and community

    oai_token-act-pair · gpt-3.5-turbo

    mentions of societal and communal concepts related to the public and collective opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.94
     Sheet
    -0.66
     Ital
    -0.65
     Croatian
    -0.65
     Rhodes
    -0.62
     tile
    -0.62
     Yugoslav
    -0.62
     Kik
    -0.61
     Slug
    -0.60
     Kah
    -0.60
    POSITIVE LOGITS
     attention
    0.90
     clam
    0.90
     perception
    0.90
     perceive
    0.87
     perceptions
    0.85
     outcry
    0.84
     reaction
    0.81
     acclaim
    0.81
     distrust
    0.80
    ankind
    0.80
    Act Density 0.551%

    No Known Activations