© 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. 1586
    Prev
    Next
    INDEX
    Explanations

    markers or indicators of societal events and circumstances

    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
    natureconservancy
    -0.76
     respectively
    -0.74
    nown
    -0.70
    channelAvailability
    -0.69
     cele
    -0.63
    uyomi
    -0.62
     tomorrow
    -0.62
    soever
    -0.61
     Shutterstock
    -0.60
     Proxy
    -0.59
    POSITIVE LOGITS
    oration
    0.71
    oling
    0.64
    choes
    0.62
    rex
    0.61
    cipl
    0.60
    luster
    0.59
    orative
    0.59
    ont
    0.58
    aches
    0.58
    chrom
    0.58
    Activations Density 0.219%

    No Known Activations