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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 22
    Prev
    Next
    INDEX
    Explanations

    terms related to financial costs and expenditures

    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
    FTWARE
    -0.89
    ----------------------------------------------------------------
    -0.74
    wind
    -0.71
    mount
    -0.69
    ======
    -0.67
    TON
    -0.64
    ECD
    -0.62
    cart
    -0.60
    VILLE
    -0.60
    gear
    -0.60
    POSITIVE LOGITS
     Announce
    0.72
     estimation
    0.70
     guiActiveUn
    0.69
    antha
    0.67
    Helper
    0.66
    uz
    0.65
     locality
    0.63
    asus
    0.62
    uca
    0.62
     Conversation
    0.61
    Activations Density 0.068%

    No Known Activations