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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cultural elements

    oai_token-act-pair · gpt-3.5-turbo

    references to culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heed
    -0.83
    ded
    -0.80
    headers
    -0.75
    ding
    -0.72
    acements
    -0.68
    idia
    -0.67
     deduct
    -0.66
    ishable
    -0.65
    berries
    -0.63
    sort
    -0.63
    POSITIVE LOGITS
     culture
    1.07
     Culture
    1.02
     cultures
    0.79
    culture
    0.76
    ulture
    0.75
     Appropri
    0.73
    uria
    0.73
     heritage
    0.71
    lia
    0.70
     Infrastructure
    0.69
    Act Density 0.017%

    No Known Activations