© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1007
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of systems and methods related to social organization and control

    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
    GN
    -0.70
    kat
    -0.67
    par
    -0.66
    helial
    -0.65
    izards
    -0.63
    audi
    -0.63
    olf
    -0.62
    stars
    -0.62
    cha
    -0.62
    ims
    -0.61
    POSITIVE LOGITS
     containment
    0.78
     raiding
    0.77
     Monitoring
    0.76
     communication
    0.74
    rification
    0.74
     engagement
    0.70
     settling
    0.69
     delivery
    0.69
     leveling
    0.69
     tradem
    0.67
    Activations Density 0.073%

    No Known Activations