© 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. 923
    Prev
    Next
    INDEX
    Explanations

    references to specific topics and detailed discussions in articles

    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
    bugs
    -0.71
    iversary
    -0.69
     Grateful
    -0.63
     foreseeable
    -0.61
    owing
    -0.60
    opped
    -0.59
    ynski
    -0.58
    dullah
    -0.58
    ames
    -0.58
    eln
    -0.56
    POSITIVE LOGITS
    Below
    0.88
     Below
    0.87
     ranging
    0.83
    >>>
    0.80
     Including
    0.78
    depth
    0.73
    Here
    0.71
     Among
    0.71
    including
    0.69
    here
    0.69
    Activations Density 1.455%

    No Known Activations