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

    Neuronpedia

    INDEX
    Explanations

    explanations involving technical or scientific discussions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    +#+#
    -0.72
     Puis
    -0.62
    MLLoader
    -0.61
    ItemBackground
    -0.61
    Puis
    -0.60
    anzia
    -0.59
    发表于
    -0.59
     Socialista
    -0.57
     بيها
    -0.57
     varandra
    -0.57
    POSITIVE LOGITS
     Apart
    1.98
     Aside
    1.93
    Aside
    1.91
    Apart
    1.79
    apart
    0.85
    apimachinery
    0.73
    RenderAtEndOf
    0.69
    ConstraintMaker
    0.67
    Along
    0.60
    Alongside
    0.59
    Act Density 0.002%

    No Known Activations