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

    Neuronpedia

    INDEX
    Explanations

    expressions and concepts related to judgment and criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pesan
    -0.15
    917
    -0.14
    æµľ
    -0.14
    occo
    -0.14
    527
    -0.14
     UPC
    -0.13
    OMIC
    -0.13
    537
    -0.13
    ê¹Ģ
    -0.13
    OURCE
    -0.13
    POSITIVE LOGITS
    ÐľÐŀ
    0.15
    ë
    0.14
    orn
    0.14
    tober
    0.14
    ulpt
    0.14
    enegro
    0.13
     Clair
    0.13
     foreign
    0.13
    les
    0.13
    empre
    0.13
    Act Density 0.214%

    No Known Activations