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

    Neuronpedia

    INDEX
    Explanations

    names that contain the repeated pattern "r9"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "r"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EntityItem
    -0.72
    £ı
    -0.72
    æĸ¹
    -0.65
    éĹĺ
    -0.63
    eers
    -0.63
     cov
    -0.63
     CPR
    -0.63
     largeDownload
    -0.63
     Contra
    -0.61
     curs
    -0.61
    POSITIVE LOGITS
    abbit
    1.23
    acing
    1.21
    agnar
    1.16
    angers
    1.15
    ifts
    1.13
    ussia
    1.11
    ach
    1.11
    agh
    1.10
    ific
    1.09
    ansom
    1.08
    Act Density 0.033%

    No Known Activations