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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 174
    Prev
    Next
    INDEX
    Explanations

    references to the Soviet Union

    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
    arsity
    -0.91
    udi
    -0.86
    ino
    -0.83
    izen
    -0.81
    iko
    -0.77
    iel
    -0.76
    olo
    -0.75
    redd
    -0.75
    iquette
    -0.72
    9999
    -0.72
    POSITIVE LOGITS
     debilitating
    0.62
     stimulus
    0.62
    Created
    0.61
     Union
    0.61
     fidelity
    0.59
    ────
    0.59
    ====
    0.59
     replay
    0.59
     allowance
    0.58
    Favorite
    0.58
    Activations Density 0.086%

    No Known Activations