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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 410
    Prev
    Next
    INDEX
    Explanations

    financial commitments and allocations

    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
    oland
    -0.69
    ascular
    -0.66
    MODE
    -0.64
    otypes
    -0.63
    psc
    -0.62
    essor
    -0.60
    sit
    -0.57
    assies
    -0.57
     categor
    -0.57
    irus
    -0.56
    POSITIVE LOGITS
     money
    1.28
     bucks
    1.13
     dollars
    1.12
     funds
    1.11
     $$
    1.06
     Money
    1.04
    money
    1.04
     Dollars
    1.01
     resources
    1.00
     proceeds
    0.99
    Activations Density 0.914%

    No Known Activations