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

    Neuronpedia

    INDEX
    Explanations

    statistical terms and phrases related to proportions and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zik
    -0.17
    elin
    -0.17
    cape
    -0.16
    ei
    -0.15
    spark
    -0.15
    scape
    -0.14
    \Collections
    -0.14
    zas
    -0.14
    haven
    -0.14
    fung
    -0.14
    POSITIVE LOGITS
     (%)
    0.20
    ally
    0.19
    oft
    0.19
    ake
    0.18
    ately
    0.18
    hood
    0.16
    /div
    0.15
    ä¹ĭä¸Ģ
    0.15
    ALLY
    0.15
    íĺķ
    0.15
    Act Density 0.051%

    No Known Activations