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. 369
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Fil" followed by numerical values or related terms

    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
     CLSID
    -0.62
     thereto
    -0.60
     wouldn
    -0.58
     couldn
    -0.58
    xual
    -0.57
     hasn
    -0.57
    RGB
    -0.56
     weren
    -0.56
     proves
    -0.56
    arily
    -0.56
    POSITIVE LOGITS
    sted
    0.74
    osi
    0.71
    lems
    0.71
    sheet
    0.68
    amber
    0.68
    ressive
    0.65
    istries
    0.64
    board
    0.64
    amental
    0.64
    lement
    0.64
    Activations Density 0.039%

    No Known Activations