Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 271
    Prev
    Next
    INDEX
    Explanations

    references to something being an integral or essential component of various contexts

    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
    errilla
    -0.70
    orget
    -0.64
     MFT
    -0.59
    wolf
    -0.58
     footing
    -0.57
    ategory
    -0.56
     Bye
    -0.55
     passive
    -0.55
     Neighbor
    -0.54
    aiden
    -0.54
    POSITIVE LOGITS
    ibur
    0.79
     of
    0.74
    iffe
    0.69
    ulations
    0.68
    of
    0.67
    usions
    0.67
    np
    0.67
    uma
    0.66
    ships
    0.65
    APD
    0.64
    Activations Density 0.032%

    No Known Activations