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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 848
    Prev
    Next
    INDEX
    Explanations

    instances of the word "record" in various contexts of achievements or metrics

    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
    video
    -0.73
    stories
    -0.70
    BRE
    -0.70
    itals
    -0.69
    words
    -0.66
    >[
    -0.65
    wcs
    -0.59
    sci
    -0.59
    mass
    -0.58
    wav
    -0.58
    POSITIVE LOGITS
    abeth
    0.70
    inkle
    0.68
     Baal
    0.68
    anges
    0.68
    ithing
    0.66
    assad
    0.63
     prices
    0.62
     lashes
    0.62
     Installation
    0.61
     revenues
    0.59
    Activations Density 0.020%

    No Known Activations