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

    Neuronpedia

    INDEX
    Explanations

    repetitions of personal pronouns and elements related to programming functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mbH
    -0.18
    peg
    -0.15
    ë¶Ī
    -0.15
    .ax
    -0.14
    LOOR
    -0.14
    .cy
    -0.14
    eur
    -0.14
    upe
    -0.13
    uong
    -0.13
    mong
    -0.13
    POSITIVE LOGITS
    radient
    0.15
    ober
    0.15
    urence
    0.14
    ÐĴÑĸн
    0.14
    tlement
    0.14
    ##_
    0.14
    رسÛĮ
    0.14
    ÙĨÛĮÙĨ
    0.14
    amina
    0.13
    ัà¸ĩส
    0.13
    Act Density 0.003%

    No Known Activations