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

    Neuronpedia

    INDEX
    Explanations

    significant nouns and proper nouns in the context of storytelling or description

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙħÛĮ
    -0.16
    ssp
    -0.15
    ONTAL
    -0.15
    ivas
    -0.14
    itter
    -0.14
    READING
    -0.14
    æĿĤ
    -0.14
    ingleton
    -0.14
    CustomLabel
    -0.13
     ol
    -0.13
    POSITIVE LOGITS
    tember
    0.16
     Cra
    0.15
    ãģŁ
    0.15
    ãģ¨ãĤĤ
    0.14
    rf
    0.14
     Pod
    0.14
    à¹Ģà¸ļ
    0.13
    ajor
    0.13
    AFX
    0.13
    innacle
    0.13
    Act Density 0.000%

    No Known Activations