© 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. 1304
    Prev
    Next
    INDEX
    Explanations

    instances of communication or discussions

    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
    orious
    -0.78
    wake
    -0.72
    nown
    -0.70
    pec
    -0.66
    enment
    -0.65
    omore
    -0.65
    ende
    -0.65
    emort
    -0.64
    theless
    -0.64
    ngth
    -0.63
    POSITIVE LOGITS
     privately
    0.61
    isance
    0.56
     toll
    0.55
    Spread
    0.55
    duction
    0.55
     playground
    0.55
     statically
    0.54
     Range
    0.53
    ucing
    0.53
    icut
    0.53
    Activations Density 0.042%

    No Known Activations