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

    Neuronpedia

    INDEX
    Explanations

    references to different tribes

    oai_token-act-pair · gpt-3.5-turbo

    references to indigenous tribes and their cultural significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vanity
    -0.76
     FANTASY
    -0.66
    eger
    -0.64
    ibrary
    -0.63
    rontal
    -0.62
     istg
    -0.60
    ials
    -0.59
     Kramer
    -0.58
     disclosures
    -0.58
     outcomes
    -0.58
    POSITIVE LOGITS
    members
    1.03
    naire
    0.96
    mates
    0.92
    men
    0.92
    lings
    0.91
     Called
    0.89
    folk
    0.88
    wana
    0.85
    keeper
    0.85
     elders
    0.83
    Act Density 0.016%

    No Known Activations