© 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. 3181
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Bel" possibly related to belief or belief systems

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     surpr
    -0.75
    respond
    -0.71
     Huck
    -0.63
     staging
    -0.63
    onduct
    -0.59
     Rarity
    -0.59
    l
    -0.58
     persist
    -0.57
     ante
    -0.55
     Yue
    -0.55
    POSITIVE LOGITS
    aqu
    0.83
    vation
    0.79
    ved
    0.78
    avez
    0.78
    XM
    0.77
    eri
    0.75
    ted
    0.73
    iron
    0.72
    kn
    0.71
    yards
    0.71
    Activations Density 0.010%

    No Known Activations