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

    Neuronpedia

    INDEX
    Explanations

    quantitative relationships and correlations between variables in scientific data

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     an
    -0.52
     statistically
    -0.50
     significantly
    -0.44
    entlicher
    -0.44
     κό
    -0.44
     Unters
    -0.43
     statistical
    -0.43
    лер
    -0.42
     Mund
    -0.42
     gender
    -0.42
    POSITIVE LOGITS
     للمعارف
    0.76
    BeginContext
    0.75
    makeConstraints
    0.75
     <=",
    0.75
     HasFactory
    0.75
     ModelExpression
    0.75
    المناصب
    0.75
    χρι
    0.73
     stället
    0.72
     CGSize
    0.69
    Act Density 0.074%

    No Known Activations