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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 628
    Prev
    Next
    INDEX
    Explanations

    references to free speech and its protections

    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
    DragonMagazine
    -0.82
    hemy
    -0.74
    Witness
    -0.72
    iop
    -0.72
     Facts
    -0.70
     VIDE
    -0.68
    ocaust
    -0.68
    govtrack
    -0.67
    Jew
    -0.67
    ewitness
    -0.67
    POSITIVE LOGITS
     calibr
    0.76
     coerc
    0.75
    andon
    0.70
     levers
    0.68
    duino
    0.66
     prolifer
    0.66
     constructs
    0.64
     conting
    0.64
     clamp
    0.63
     mounts
    0.62
    Activations Density 0.359%

    No Known Activations