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

    Neuronpedia

    INDEX
    Explanations

    structured phrases and terms related to administrative or organizational processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yg
    -0.15
    and
    -0.15
     Bri
    -0.14
    sek
    -0.14
    -el
    -0.14
    <br
    -0.14
    sun
    -0.13
    иÑģÑĤÑĢа
    -0.13
    íĥķ
    -0.13
     ï¼
    -0.13
    POSITIVE LOGITS
     or
    0.27
    æĪĸ
    0.24
     или
    0.23
    æĪĸèĢħ
    0.23
     oder
    0.23
     hoặc
    0.22
     ÛĮا
    0.21
     або
    0.21
     æĪĸ
    0.21
     atau
    0.20
    Act Density 0.015%

    No Known Activations