© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 657
    Prev
    Next
    INDEX
    Explanations

    superlative expressions indicating the "most" of something

    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
    EStream
    -0.90
    lace
    -0.76
    isSpecialOrderable
    -0.73
     Dwell
    -0.71
     Release
    -0.68
    cffffcc
    -0.68
    Leaks
    -0.66
    elight
    -0.66
    arity
    -0.66
    Activity
    -0.65
    POSITIVE LOGITS
     important
    0.79
     satisfying
    0.76
     unpredictable
    0.74
     heinous
    0.74
     humane
    0.73
     dangerous
    0.73
     terrifying
    0.73
     qualified
    0.73
     indistinguishable
    0.73
     frightening
    0.72
    Activations Density 0.037%

    No Known Activations