© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1387
    Prev
    Next
    INDEX
    Explanations

    concepts related to ethics and social justice

    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
     sidx
    -0.84
    ainers
    -0.82
     chairs
    -0.74
    wagon
    -0.70
    bye
    -0.69
     Means
    -0.69
    rals
    -0.68
    leck
    -0.67
    queue
    -0.66
    qqa
    -0.65
    POSITIVE LOGITS
     irrelevant
    0.90
     nonexistent
    0.75
     vit
    0.72
     dependent
    0.71
     FAR
    0.70
     faked
    0.70
    omorph
    0.70
     incompatible
    0.69
     synonymous
    0.68
     laced
    0.68
    Activations Density 0.292%

    No Known Activations