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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 287
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in an incident or situation

    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
    200000
    -0.73
    ECTION
    -0.68
     subdivision
    -0.68
     photograp
    -0.67
     spotting
    -0.66
     prescribing
    -0.65
    vt
    -0.65
    ASED
    -0.63
     enforcing
    -0.63
     jurisdiction
    -0.62
    POSITIVE LOGITS
     underwent
    0.88
     survived
    0.87
     fell
    0.78
     remained
    0.77
     survives
    0.75
     wandered
    0.75
     died
    0.74
     remains
    0.73
     endured
    0.72
     breaths
    0.72
    Activations Density 0.398%

    No Known Activations