© 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. 1044
    Prev
    Next
    INDEX
    Explanations

    the word "those" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     tremend
    -0.81
    yip
    -0.77
    etheus
    -0.76
    aucus
    -0.74
    peria
    -0.73
     unden
    -0.72
    ModLoader
    -0.71
     earthqu
    -0.70
    cca
    -0.70
    ��極
    -0.70
    POSITIVE LOGITS
     counterparts
    0.94
     results
    0.86
     rounds
    0.86
     equivalents
    0.86
     terms
    0.82
     tables
    0.81
     slots
    0.79
     duties
    0.79
     mechanisms
    0.78
     accounts
    0.78
    Activations Density 0.057%

    No Known Activations