© 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. 3260
    Prev
    Next
    INDEX
    Explanations

    qualities related to effective communication and consistency

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Strength
    -0.61
     Presence
    -0.58
    rals
    -0.58
    chest
    -0.56
    iframe
    -0.55
     Finish
    -0.54
    rame
    -0.54
    ieth
    -0.52
    mpeg
    -0.52
     Appears
    -0.52
    POSITIVE LOGITS
    ghazi
    0.64
    bye
    0.61
     paced
    0.58
    alla
    0.58
    Guest
    0.58
    ALLY
    0.57
    lich
    0.57
    atos
    0.55
    ergy
    0.54
    fox
    0.54
    Activations Density 0.922%

    No Known Activations