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

    Neuronpedia

    INDEX
    Explanations

    references to publication formats or indicators of page numbers in academic articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    931
    -0.15
    nten
    -0.14
    artner
    -0.14
    òn
    -0.14
    IMO
    -0.13
    ¿
    -0.13
    athe
    -0.13
    roupe
    -0.13
    afa
    -0.13
     Atomic
    -0.13
    POSITIVE LOGITS
    ModelProperty
    0.16
    ëĬIJ
    0.15
    issing
    0.15
    ëĨ
    0.14
     cứng
    0.13
    istrovstvÃŃ
    0.13
    ç«¥
    0.13
    utra
    0.13
    ysize
    0.13
    Routes
    0.13
    Act Density 0.006%

    No Known Activations