Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 74
    Prev
    Next
    INDEX
    Explanations

    statements about advancements or changes over time, particularly in technology or social 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
    rals
    -0.74
    =-=-
    -0.63
    onies
    -0.61
    bash
    -0.61
     Wis
    -0.60
    saf
    -0.59
     Grounds
    -0.58
     Normally
    -0.58
    olan
    -0.58
    neg
    -0.58
    POSITIVE LOGITS
    increasing
    1.09
     trend
    0.98
     evolving
    0.97
     revolution
    0.97
    Demand
    0.96
     renaissance
    0.94
     decreasing
    0.91
     changing
    0.91
     Increasing
    0.90
     increasing
    0.90
    Activations Density 2.582%

    No Known Activations