© 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. 2812
    Prev
    Next
    INDEX
    Explanations

    phrases that denote accessibility and ease of use in transactions

    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
    established
    -0.77
    alian
    -0.74
    ammed
    -0.72
    astical
    -0.69
    Examples
    -0.69
    rosso
    -0.67
    ream
    -0.67
    ocument
    -0.65
    DragonMagazine
    -0.65
    cele
    -0.64
    POSITIVE LOGITS
    erous
    0.79
    advertising
    0.69
     intermedi
    0.68
     lid
    0.67
     overhead
    0.67
     bothering
    0.66
    rawdownloadcloneembedreportprint
    0.64
     ceiling
    0.64
     burdens
    0.63
     burd
    0.62
    Activations Density 0.196%

    No Known Activations