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

    Neuronpedia

    INDEX
    Explanations

    references to significant innovations or advancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (utf
    -0.17
    une
    -0.16
    à¸Ńà¹Ģร
    -0.15
    енÑĤÑĥ
    -0.14
    aiser
    -0.14
     Voj
    -0.14
    ismatch
    -0.13
    UNE
    -0.13
    ast
    -0.13
     Loft
    -0.13
    POSITIVE LOGITS
    ISTA
    0.16
    reesome
    0.15
    grade
    0.15
    eve
    0.15
    ista
    0.14
    ghi
    0.14
    ritz
    0.14
    -through
    0.14
    ä¸ģ
    0.14
    alus
    0.13
    Act Density 0.003%

    No Known Activations