© 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. 901
    Prev
    Next
    INDEX
    Explanations

    references to items or entities in a structured format or context

    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
    're
    -0.71
     ARE
    -0.71
    are
    -0.67
    were
    -0.66
    anners
    -0.66
     challeng
    -0.64
    lace
    -0.63
     proport
    -0.62
    aspers
    -0.62
     aren
    -0.62
    POSITIVE LOGITS
     involves
    0.93
     depends
    0.85
     varies
    0.83
     is
    0.82
     requires
    0.79
     constitutes
    0.78
     doubles
    0.78
     extends
    0.77
     was
    0.77
    was
    0.75
    Activations Density 2.549%

    No Known Activations