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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Du" followed by a single digit at the end

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Du" followed by various terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     crore
    -0.75
    iband
    -0.71
    âĢİ
    -0.70
    PATH
    -0.69
    SHIP
    -0.67
    oked
    -0.65
     bothered
    -0.65
    Spoiler
    -0.65
    ared
    -0.64
    oky
    -0.64
    POSITIVE LOGITS
     Du
    3.74
    Du
    2.73
     du
    1.96
     DU
    1.51
     Duo
    1.21
    du
    1.21
     Dup
    1.17
     Dul
    1.16
     Dor
    1.15
     Dow
    1.12
    Act Density 0.019%

    No Known Activations