© 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. 813
    Prev
    Next
    INDEX
    Explanations

    references to various leagues and organizations

    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
    forcement
    -0.77
     gauge
    -0.72
     counselor
    -0.69
     resusc
    -0.68
     warmer
    -0.68
     restart
    -0.67
     sponsor
    -0.66
    yip
    -0.65
     microscope
    -0.64
    combe
    -0.62
    POSITIVE LOGITS
     Authorities
    0.83
     Customers
    0.79
     VIDEOS
    0.78
     Classes
    0.74
    Residents
    0.73
    types
    0.73
    uders
    0.73
    Stars
    0.73
     Users
    0.73
    Cath
    0.73
    Activations Density 0.022%

    No Known Activations