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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2594
    Prev
    Next
    INDEX
    Explanations

    unusual or atypical characters and symbols

    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
     flourish
    -0.72
     repe
    -0.72
     revolt
    -0.72
     dram
    -0.71
     vo
    -0.71
     spark
    -0.69
     revol
    -0.69
     siph
    -0.68
     plot
    -0.67
     rebell
    -0.67
    POSITIVE LOGITS
    And
    1.24
    Either
    1.20
    People
    1.18
    Especially
    1.18
    Cod
    1.16
    We
    1.15
    Any
    1.15
    Also
    1.14
    Kind
    1.13
    For
    1.13
    Activations Density 0.091%

    No Known Activations