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

    Neuronpedia

    INDEX
    Explanations

    descriptors indicating complexity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     typelib
    -0.51
     pinulongan
    -0.51
     noDo
    -0.50
     Italijanski
    -0.47
    Välislingid
    -0.47
    GEBURTSDATUM
    -0.45
    makeConstraints
    -0.43
    ConstraintMaker
    -0.41
     Paglinawan
    -0.40
    lardır
    -0.38
    POSITIVE LOGITS
    XmlType
    0.76
     للاسماء
    0.56
     complex
    0.54
     Complex
    0.53
    Complex
    0.51
    ArgumentParser
    0.51
    complex
    0.50
     compleja
    0.44
    asinya
    0.44
     intricate
    0.44
    Act Density 0.161%

    No Known Activations