© 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. 1058
    Prev
    Next
    INDEX
    Explanations

    phrases expressing recommendations and warnings regarding content

    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
    tein
    -0.65
     stabilization
    -0.58
    nam
    -0.56
     Parliament
    -0.56
     Currency
    -0.55
     redistributed
    -0.55
    quickShipAvailable
    -0.55
    fred
    -0.54
     promises
    -0.53
     Alc
    -0.53
    POSITIVE LOGITS
     beware
    0.87
     notor
    0.77
    avoid
    0.77
     viewing
    0.73
     heed
    0.72
    erning
    0.71
     reading
    0.71
     savvy
    0.70
     exerc
    0.69
     patience
    0.69
    Activations Density 1.632%

    No Known Activations