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. 297
    Prev
    Next
    INDEX
    Explanations

    references to discovery or recovery of physical objects, particularly in a context related to remains or artifacts

    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
    生
    -0.77
     amino
    -0.77
     anth
    -0.70
     acids
    -0.69
     chalk
    -0.66
    oil
    -0.65
     dstg
    -0.64
     Ceres
    -0.64
    itol
    -0.64
     boosters
    -0.63
    POSITIVE LOGITS
    posed
    0.74
    Bern
    0.72
    Scan
    0.71
    proxy
    0.70
     filtering
    0.68
    Ability
    0.66
    attr
    0.66
    Send
    0.66
    defined
    0.65
    Downloadha
    0.65
    Activations Density 0.654%

    No Known Activations