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

    Neuronpedia

    INDEX
    Explanations

    quantitative measures related to fractions and percentages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uurs
    -0.40
     montagna
    -0.37
     chapter
    -0.36
    nezeu
    -0.35
     gemeente
    -0.33
     stiamo
    -0.31
     στι
    -0.30
     opge
    -0.29
     capítulo
    -0.29
    writel
    -0.29
    POSITIVE LOGITS
     Percentage
    0.92
     percentage
    0.91
    Percentage
    0.86
     percentages
    0.86
    percentage
    0.86
     (%)
    0.84
     Percent
    0.83
     porcentaje
    0.82
     percent
    0.81
    percent
    0.78
    Act Density 1.887%

    No Known Activations