© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1288
    Prev
    Next
    INDEX
    Explanations

    references to scientific methodologies and statistical data

    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
     chats
    -0.68
     presence
    -0.67
     webcam
    -0.66
     capacitor
    -0.65
     houses
    -0.64
     interceptions
    -0.62
     pics
    -0.62
     interception
    -0.61
     Spaces
    -0.61
     weekends
    -0.61
    POSITIVE LOGITS
    undo
    0.89
    amen
    0.88
    pers
    0.86
    enough
    0.84
    aye
    0.84
    minded
    0.83
    ascript
    0.80
    meaning
    0.79
    Catalog
    0.78
    iHUD
    0.78
    Activations Density 0.039%

    No Known Activations