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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recognition or fame, particularly in relation to notable individuals' accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oz
    -0.16
    OF
    -0.16
     subparagraph
    -0.15
    amer
    -0.15
    usted
    -0.15
    rof
    -0.15
    alice
    -0.14
    à¹īำ
    -0.14
    orch
    -0.14
    -UA
    -0.13
    POSITIVE LOGITS
    awa
    0.17
     Entrance
    0.15
    heim
    0.15
    landers
    0.15
    rance
    0.14
    ÙģÙĩ
    0.14
    748
    0.14
    ifi
    0.14
    719
    0.14
    uku
    0.13
    Act Density 0.076%

    No Known Activations