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

    Neuronpedia

    INDEX
    Explanations

    references to significant accomplishments or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vere
    -0.17
    hangi
    -0.15
    yleft
    -0.15
    ledge
    -0.15
    uck
    -0.15
    ehir
    -0.15
    APPER
    -0.14
    uentes
    -0.14
    DDD
    -0.14
    ypes
    -0.14
    POSITIVE LOGITS
     unm
    0.15
    abela
    0.14
    ียà¸Ķ
    0.14
    niej
    0.14
    rost
    0.14
    екаÑĢ
    0.14
    iesta
    0.14
    unday
    0.14
    %S
    0.13
    ล
    0.13
    Act Density 0.006%

    No Known Activations