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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names of individuals, particularly focusing on the last names starting with the letter "D"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.75
    jri
    -0.73
     commissions
    -0.67
    querade
    -0.66
    agall
    -0.65
     sher
    -0.64
    icip
    -0.64
     cess
    -0.64
    é¾įå¥ij士
    -0.61
     Mehran
    -0.61
    POSITIVE LOGITS
    ãĥķãĤ©
    0.76
    ãĤ¶
    0.72
    ãĥ¼ãĥĨ
    0.71
    ãĤ¿
    0.70
    ãĥ¡
    0.68
    ãĤ¨ãĥ«
    0.67
    ãĥ¼ãĥ
    0.66
    ãĥĺ
    0.66
    atz
    0.65
    ãĤ«
    0.65
    Act Density 0.406%

    No Known Activations