© 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. 827
    Prev
    Next
    INDEX
    Explanations

    emotions related to negative reactions or responses

    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
     reuse
    -0.76
     interoper
    -0.70
     perman
    -0.68
     discipline
    -0.62
     flexibility
    -0.62
     grammar
    -0.62
    ibl
    -0.61
     reliability
    -0.60
    afe
    -0.59
     clipping
    -0.59
    POSITIVE LOGITS
    aukee
    0.76
    Reviewer
    0.70
    enza
    0.67
    -->
    0.66
    felt
    0.66
    ensable
    0.65
    1001
    0.65
    -----------
    0.65
    enson
    0.64
    enegger
    0.64
    Activations Density 0.118%

    No Known Activations