© 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. 1386
    Prev
    Next
    INDEX
    Explanations

    symbols or specific characters that may signify unique formatting or categorization

    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
    cerning
    -0.60
    ares
    -0.60
    ulent
    -0.59
    uala
    -0.59
    ent
    -0.58
    ensible
    -0.57
    schild
    -0.57
    ibles
    -0.57
    izes
    -0.56
    ilib
    -0.56
    POSITIVE LOGITS
    PDATE
    0.80
     reluct
    0.71
     Citiz
    0.68
     looph
    0.67
     Griff
    0.64
    HTTP
    0.62
     corrid
    0.61
    SHARE
    0.60
    ItemThumbnailImage
    0.59
     Spoiler
    0.59
    Activations Density 0.171%

    No Known Activations