© 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. 470
    Prev
    Next
    INDEX
    Explanations

    phrases that reference citations or sources of information

    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
    igor
    -0.79
    iour
    -0.78
    effects
    -0.70
    フォ
    -0.70
    inventoryQuantity
    -0.68
    iors
    -0.67
    nature
    -0.65
    fore
    -0.65
    �
    -0.61
    icult
    -0.61
    POSITIVE LOGITS
     study
    0.84
     questionnaire
    0.78
     BuzzFeed
    0.75
     memorandum
    0.74
     photograph
    0.73
     document
    0.71
     tweet
    0.71
     conversation
    0.71
     1986
    0.70
     report
    0.70
    Activations Density 0.230%

    No Known Activations