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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters or identifiers that appear to follow a specific coding or formatting pattern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    trie
    -0.15
    ήν
    -0.14
    hq
    -0.14
     SSE
    -0.14
    pose
    -0.13
    Eta
    -0.13
     @}
    -0.13
    ÑĨеÑĢ
    -0.13
    ostel
    -0.13
    IAN
    -0.13
    POSITIVE LOGITS
    ates
    0.17
    .signals
    0.15
    anas
    0.15
     Fé
    0.14
     inev
    0.14
    Defaults
    0.14
    çª
    0.14
    ATES
    0.14
    unifu
    0.14
    illas
    0.14
    Act Density 0.004%

    No Known Activations