© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3226
    Prev
    Next
    INDEX
    Explanations

    concepts related to novelty or newness

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    respond
    -0.80
    laws
    -0.79
    mails
    -0.76
     repairs
    -0.72
     Citiz
    -0.71
    ascript
    -0.70
    existing
    -0.67
     Related
    -0.65
    reditary
    -0.64
     tied
    -0.63
    POSITIVE LOGITS
     era
    0.92
     avenue
    0.88
     frontier
    0.79
     paradigm
    0.78
     norm
    0.76
     vantage
    0.75
     heights
    0.75
     battleground
    0.72
     archetype
    0.71
     heroine
    0.71
    Activations Density 0.057%

    No Known Activations