© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 2023
    Prev
    Next
    INDEX
    Explanations

    `str.join` with `random.choice` (negative activations)

    python-code · gemini-2.5-flash-lite

    list casting

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...
    -0.13
     other
    -0.09
    ["
    -0.07
     is
    -0.06
    ['
    -0.06
     as
    -0.06
    .items
    -0.06
    .get
    -0.02
    '
    0.00
    #
    0.00
    POSITIVE LOGITS
     +
    0.22
    +
    0.22
     +=
    0.20
    [(
    0.10
     main
    0.10
    [:
    0.08
    {
    0.08
     !=
    0.05
     current
    0.03
    <extra_output_id:2047>
    0.02
    Activations Density 100.000%

    No Known Activations