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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2422
    Prev
    Next
    INDEX
    Explanations

    concepts related to power dynamics and authority

    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
    emetery
    -0.67
    oult
    -0.63
    These
    -0.62
    yssey
    -0.61
    these
    -0.60
    esis
    -0.59
     respectively
    -0.57
     actionGroup
    -0.56
    haus
    -0.55
    amba
    -0.54
    POSITIVE LOGITS
     it
    1.48
     It
    1.01
    It
    0.89
    it
    0.82
     IT
    0.69
    Its
    0.68
    itan
    0.66
    ilial
    0.64
     Its
    0.62
     its
    0.61
    Activations Density 3.125%

    No Known Activations