© 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. 3168
    Prev
    Next
    INDEX
    Explanations

    mentions of "the" in relation to newness or familiarity with a specific topic

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    Haunted
    -0.83
    Dialogue
    -0.82
    Spider
    -0.79
    CHR
    -0.78
    lag
    -0.77
    TPPStreamerBot
    -0.77
    nyder
    -0.77
    ijn
    -0.74
    allic
    -0.73
    illes
    -0.72
    POSITIVE LOGITS
     undertaking
    0.87
     Realms
    0.82
     system
    0.80
     band
    0.80
     firm
    0.79
     hobby
    0.77
     acronym
    0.76
     outlet
    0.75
     institution
    0.75
     station
    0.73
    Activations Density 0.320%

    No Known Activations