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

    Neuronpedia

    INDEX
    Explanations

    references to selection filters or menu options within a dataset or archive

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    за
    -0.16
    ëł´
    -0.15
    alian
    -0.15
     Borg
    -0.15
    Å©
    -0.15
    uster
    -0.14
    ube
    -0.14
    erior
    -0.14
     loc
    -0.14
    itez
    -0.14
    POSITIVE LOGITS
    leet
    0.16
    dere
    0.15
    Library
    0.15
    rese
    0.14
    cov
    0.14
    ³³
    0.14
    chein
    0.14
    uar
    0.13
    æ³ī
    0.13
    avras
    0.13
    Act Density 0.004%

    No Known Activations