© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 806
    Prev
    Next
    INDEX
    Explanations

    numerical values or quantities in the text

    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
     fragmentation
    -0.91
     yes
    -0.82
     monopol
    -0.75
     plurality
    -0.75
     generalized
    -0.74
     systematic
    -0.74
     extremes
    -0.73
     privately
    -0.72
     clones
    -0.72
     metic
    -0.72
    POSITIVE LOGITS
    AZ
    1.14
    Exit
    1.12
    Mat
    1.12
    Pass
    1.11
    Snow
    1.10
    Poor
    1.10
    Ball
    1.09
    Bridge
    1.09
    Image
    1.08
    Gall
    1.08
    Activations Density 0.402%

    No Known Activations