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

    Neuronpedia

    INDEX
    Explanations

    references to unlawful actions or situations related to authority or governance

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Хьажоргаш
    -1.09
     GenerationType
    -0.91
     esternos
    -0.89
    WithIOException
    -0.83
     للمعارف
    -0.79
     NSCoder
    -0.78
     resourceCulture
    -0.74
    ########.
    -0.74
     Chriftian
    -0.73
    Espèce
    -0.72
    POSITIVE LOGITS
     dem
    0.55
    hö
    0.50
    devamını
    0.49
    ’
    0.48
     –
    0.45
    :
    0.43
     tri
    0.43
    mp
    0.42
    pl
    0.42
     Dem
    0.41
    Act Density 0.051%

    No Known Activations