© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 847
    Prev
    Next
    INDEX
    Explanations

    themes related to social issues and individual experiences

    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
     challeng
    -0.40
     surpr
    -0.39
     sugg
    -0.39
     distingu
    -0.37
     occas
    -0.37
     acknow
    -0.37
     agre
    -0.36
     redes
    -0.35
     encount
    -0.34
     misunder
    -0.33
    POSITIVE LOGITS
    rage
    0.29
    delay
    0.28
    izabeth
    0.27
    acent
    0.27
    edia
    0.27
    tics
    0.26
    proof
    0.26
    scripts
    0.26
    enary
    0.25
     dummy
    0.25
    Activations Density 3.303%

    No Known Activations