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. 9-TRES-DC
    5. 663
    Prev
    Next
    INDEX
    Explanations

    financial figures or budget 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
    catentry
    -0.71
    soDeliveryDate
    -0.68
    ��
    -0.63
     continental
    -0.62
    ococ
    -0.62
    crypt
    -0.61
     tremend
    -0.60
     civilisation
    -0.59
    ��
    -0.59
    Alternatively
    -0.59
    POSITIVE LOGITS
     421
    0.90
     420
    0.88
     180
    0.88
     141
    0.87
     320
    0.86
     425
    0.85
     343
    0.85
     315
    0.85
     327
    0.85
     321
    0.85
    Activations Density 0.051%

    No Known Activations