Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 485
    Prev
    Next
    INDEX
    Explanations

    numerical data related to measurements and statistics

    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
    EngineDebug
    -0.79
    cember
    -0.59
     veter
    -0.58
     <+
    -0.55
     disadvant
    -0.54
     myster
    -0.52
    iggins
    -0.50
    iatus
    -0.50
    Bey
    -0.50
     <@
    -0.49
    POSITIVE LOGITS
     Address
    0.53
    神
    0.52
     WR
    0.50
     Commands
    0.50
    unders
    0.50
    aths
    0.50
    apt
    0.50
     Thou
    0.49
    clinical
    0.49
     Directory
    0.49
    Activations Density 0.533%

    No Known Activations