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

    Neuronpedia

    INDEX
    Explanations

    mention of countries

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the conjunction "and" followed by various nationalities or descriptors related to people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shelves
    -0.80
     horm
    -0.73
     payoff
    -0.72
     shel
    -0.72
     descriptor
    -0.71
    perty
    -0.70
     racks
    -0.70
     partitions
    -0.70
     tumors
    -0.69
    nosis
    -0.69
    POSITIVE LOGITS
    Italian
    0.96
     Croat
    0.96
    Indian
    0.92
     Anglo
    0.91
    gian
    0.91
    orean
    0.87
    German
    0.87
    English
    0.86
     Portuguese
    0.86
    Eastern
    0.85
    Act Density 0.170%

    No Known Activations