© 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. 1204
    Prev
    Next
    INDEX
    Explanations

    references to specific decades and associated cultural or historical contexts

    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
    ousand
    -0.73
     Trib
    -0.69
    aukee
    -0.68
    anz
    -0.64
    umann
    -0.64
    ivo
    -0.63
    essee
    -0.63
     Hundred
    -0.62
    ettings
    -0.62
    ippi
    -0.61
    POSITIVE LOGITS
    borne
    0.69
    danger
    0.65
     rattled
    0.64
     contr
    0.64
    bent
    0.63
    XX
    0.62
    Trend
    0.62
     destro
    0.62
     safer
    0.62
    ista
    0.60
    Activations Density 0.020%

    No Known Activations