© 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. 3117
    Prev
    Next
    INDEX
    Explanations

    terms related to questions, principles, and societal or policy issues

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    Attach
    -0.70
    ega
    -0.67
    enges
    -0.65
    hops
    -0.64
     ingred
    -0.60
    PsyNetMessage
    -0.60
     inquiries
    -0.59
     kin
    -0.59
     hybrids
    -0.58
     proxies
    -0.58
    POSITIVE LOGITS
     Dragonbound
    0.62
     Tonight
    0.59
     wildly
    0.55
    geon
    0.54
    dict
    0.54
    govern
    0.53
     Voice
    0.53
     ourselves
    0.52
     massively
    0.51
    onian
    0.51
    Activations Density 0.274%

    No Known Activations