© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2976
    Prev
    Next
    INDEX
    Explanations

    elements related to conflict and competition

    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
    inventoryQuantity
    -0.80
    worth
    -0.73
     deduction
    -0.65
    erick
    -0.65
    accompanied
    -0.64
    Section
    -0.62
    staking
    -0.61
    votes
    -0.61
    ickson
    -0.61
    illac
    -0.60
    POSITIVE LOGITS
     world
    0.93
     surroundings
    0.88
     planet
    0.87
     globe
    0.87
     audiences
    0.86
     earth
    0.84
     viewer
    0.81
     audience
    0.81
     Earth
    0.80
     viewers
    0.80
    Activations Density 2.122%

    No Known Activations