© 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. 2980
    Prev
    Next
    INDEX
    Explanations

    references to authoritative figures and their arguments

    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
     Conversion
    -0.77
    )</
    -0.76
     Smile
    -0.71
    .<
    -0.68
    ……………………
    -0.65
     Badge
    -0.65
     Delicious
    -0.65
     Wise
    -0.64
     Trinidad
    -0.63
     Renaissance
    -0.62
    POSITIVE LOGITS
     spills
    0.88
     writes
    0.86
     observes
    0.85
     contends
    0.84
     relates
    0.83
     alleges
    0.83
     argues
    0.80
     overhe
    0.79
     compares
    0.79
     asserts
    0.78
    Activations Density 0.384%

    No Known Activations