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

    Neuronpedia

    INDEX
    Explanations

    terms related to cultural aspects or elements

    oai_token-act-pair · gpt-3.5-turbo

    references to cultural themes and phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -1.00
    agher
    -0.99
    deen
    -0.82
    etsk
    -0.81
    alos
    -0.78
    ishable
    -0.78
    minster
    -0.76
    ldon
    -0.76
    vous
    -0.74
    ded
    -0.73
    POSITIVE LOGITS
     Marxism
    1.06
     heritage
    1.02
     appropriation
    0.95
     significance
    0.90
     norms
    0.89
     diversity
    0.88
     anthropology
    0.87
     competence
    0.86
    ultural
    0.83
     cac
    0.82
    Act Density 0.023%

    No Known Activations