© 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. 3123
    Prev
    Next
    INDEX
    Explanations

    fragments that denote dialogue or conversational exchanges

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     highs
    -0.62
     distances
    -0.60
     hackers
    -0.59
     demon
    -0.56
     youth
    -0.56
     hugs
    -0.56
     Cent
    -0.56
     tread
    -0.55
     whisk
    -0.54
     hikes
    -0.53
    POSITIVE LOGITS
    エル
    0.99
    til
    0.87
    ラン
    0.82
    ONSORED
    0.81
    ال
    0.77
    miah
    0.75
    ーティ
    0.72
    Liter
    0.72
     Defin
    0.72
                    
    0.71
    Activations Density 0.300%

    No Known Activations