© 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. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1124
    Prev
    Next
    INDEX
    Explanations

    specialized terminology related to neuroscience and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lished
    -0.75
     |--
    -0.71
    pling
    -0.69
    ql
    -0.67
     convinc
    -0.66
    phis
    -0.65
    QL
    -0.65
    @#&
    -0.60
    oled
    -0.60
    PROV
    -0.60
    POSITIVE LOGITS
    enty
    0.71
    amen
    0.71
    gate
    0.71
    oil
    0.70
     Invention
    0.68
    ab
    0.65
    emark
    0.64
    antly
    0.64
    ant
    0.62
    iner
    0.62
    Activations Density 1.096%

    No Known Activations