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

    Neuronpedia

    INDEX
    Explanations

    specific symbols and characters, indicating a focus on non-alphabetic content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neh
    -0.17
    ÙĪرا
    -0.15
    ickle
    -0.15
    aggio
    -0.15
    wich
    -0.14
    anh
    -0.14
    DataReader
    -0.14
    à¹ĩà¸Ķ
    -0.14
     Horton
    -0.14
    Pose
    -0.14
    POSITIVE LOGITS
    attern
    0.19
     Patent
    0.19
     issue
    0.18
     patent
    0.17
    elden
    0.17
     Issue
    0.17
    ascar
    0.17
     feed
    0.17
    atar
    0.15
    éné
    0.15
    Act Density 0.003%

    No Known Activations