© 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. 3146
    Prev
    Next
    INDEX
    Explanations

    negative statements or phrases indicating failure or lack

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    utical
    -0.69
    DragonMagazine
    -0.68
    staking
    -0.63
    DERR
    -0.61
    acha
    -0.60
     diligence
    -0.60
     specificity
    -0.58
    rely
    -0.57
     sourcing
    -0.57
    arge
    -0.56
    POSITIVE LOGITS
     padded
    0.61
     suburban
    0.56
     upd
    0.56
    Shadow
    0.56
     cheap
    0.55
     discount
    0.55
     removable
    0.55
     underestimate
    0.54
     Repeat
    0.53
    MEN
    0.52
    Activations Density 0.465%

    No Known Activations