© 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. 3034
    Prev
    Next
    INDEX
    Explanations

    sequences of characters representing brackets or special formatting

    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
     mascul
    -0.74
     disqualified
    -0.71
     insulted
    -0.71
     groom
    -0.70
     weep
    -0.69
    hement
    -0.69
     sympath
    -0.68
     offended
    -0.66
     rupt
    -0.64
     upset
    -0.63
    POSITIVE LOGITS
    Enlarge
    0.89
    drawn
    0.77
    soDeliveryDate
    0.76
    tips
    0.75
    ECTION
    0.75
    catentry
    0.74
    DIT
    0.73
    URI
    0.73
    size
    0.73
    head
    0.71
    Activations Density 0.041%

    No Known Activations