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

    Neuronpedia

    INDEX
    Explanations

    phrases related to fame and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anton
    -0.14
    ials
    -0.14
    eca
    -0.14
    umer
    -0.14
    elli
    -0.13
    queda
    -0.13
    ocalypse
    -0.13
    anca
    -0.12
    asio
    -0.12
    анка
    -0.12
    POSITIVE LOGITS
     fame
    0.53
     popularity
    0.45
     Fame
    0.38
     renown
    0.38
     recognition
    0.37
     prominence
    0.33
     status
    0.32
     visibility
    0.31
     reputation
    0.30
     success
    0.29
    Act Density 0.272%

    No Known Activations