© 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. 3006
    Prev
    Next
    INDEX
    Explanations

    titles or names associated with notable creative works and their creators

    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
     whit
    -0.73
     impression
    -0.71
     ads
    -0.65
     advertisement
    -0.63
     argument
    -0.62
     polls
    -0.61
     pros
    -0.60
     news
    -0.59
     convincing
    -0.58
     criticism
    -0.58
    POSITIVE LOGITS
    ��
    0.93
    thora
    0.92
    ��
    0.83
    ropolis
    0.80
    ゴン
    0.79
    ascript
    0.78
    ��極
    0.78
    atron
    0.77
    ��
    0.76
    ventures
    0.75
    Activations Density 0.407%

    No Known Activations