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

    Neuronpedia

    INDEX
    Explanations

    instances of clarity and performance indicators in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eo
    -0.15
    sı
    -0.15
    CellValue
    -0.14
    unga
    -0.14
    elm
    -0.14
    ago
    -0.14
    ืà¸Ļ
    -0.14
    relude
    -0.14
    ungen
    -0.14
    ienia
    -0.14
    POSITIVE LOGITS
    rosse
    0.15
     Buster
    0.15
    asty
    0.14
    ples
    0.14
    stal
    0.14
    orno
    0.13
     Cats
    0.13
    anh
    0.13
     McConnell
    0.13
     Äijang
    0.13
    Act Density 0.112%

    No Known Activations