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

    Neuronpedia

    INDEX
    Explanations

    occurrences of hash symbols and related content in textual data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lomb
    -0.15
     liqu
    -0.14
    ikk
    -0.14
    pitch
    -0.14
    oven
    -0.14
    'options
    -0.14
    laden
    -0.14
    pill
    -0.13
     modal
    -0.13
     Tenn
    -0.13
    POSITIVE LOGITS
     noqa
    0.28
     sourceMappingURL
    0.21
    rrha
    0.19
    ¥IJ
    0.17
    shire
    0.17
    DonaldTrump
    0.17
    !/
    0.17
     pylint
    0.16
    endregion
    0.16
    ï¸ı
    0.15
    Act Density 0.044%

    No Known Activations