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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to rankings and lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     figure
    -0.15
    uffers
    -0.14
    nelly
    -0.13
    cox
    -0.13
    367
    -0.13
    eters
    -0.13
     level
    -0.13
     Hra
    -0.13
    649
    -0.13
    дÑĢеÑģ
    -0.13
    POSITIVE LOGITS
     official
    0.24
     Official
    0.23
    Official
    0.19
     oficial
    0.19
    official
    0.17
     ê³µìĭĿ
    0.17
    å®ĺæĸ¹
    0.17
     رسÙħÛĮ
    0.15
    \OptionsResolver
    0.15
     unofficial
    0.15
    Act Density 0.012%

    No Known Activations