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

    Neuronpedia

    INDEX
    Explanations

    significant nouns and words related to quantity or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ferd
    -0.18
    á»iji
    -0.16
    ÏĢλα
    -0.16
    acer
    -0.16
    uti
    -0.15
    çª
    -0.15
    ÙĴÙĩ
    -0.14
    à¹Ģà¸Ĺ
    -0.14
     Resident
    -0.14
    endale
    -0.14
    POSITIVE LOGITS
     revers
    0.16
    andır
    0.16
    atory
    0.15
    ÙĪاÙĨ
    0.15
    ahu
    0.15
    etta
    0.14
     behold
    0.14
    ço
    0.14
    ija
    0.14
    ãĤĦãģĻ
    0.14
    Act Density 0.003%

    No Known Activations