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

    Neuronpedia

    INDEX
    Explanations

    references to social classes and demographic groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Comple
    -0.64
    Altre
    -0.60
     ویکی‌پدیا
    -0.56
     للاسماء
    -0.55
    yszer
    -0.54
    piecze
    -0.51
     voisins
    -0.49
     nakalista
    -0.49
    deur
    -0.49
     hjel
    -0.49
    POSITIVE LOGITS
    Datuak
    0.80
     audiences
    0.78
     citizenry
    0.78
     населення
    0.76
     populations
    0.75
     populace
    0.75
     demographics
    0.73
     masses
    0.72
     population
    0.72
     clientèle
    0.71
    Act Density 0.393%

    No Known Activations