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. 211
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and political concepts

    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
     belonging
    -0.67
     proceeding
    -0.65
     biting
    -0.65
     complying
    -0.63
     ruling
    -0.61
     wanting
    -0.59
     moving
    -0.58
     reading
    -0.58
     sticking
    -0.58
     remaining
    -0.57
    POSITIVE LOGITS
    ize
    1.19
    ify
    1.15
    ulate
    1.07
    inate
    1.04
    cknow
    1.03
    semble
    1.02
    izes
    1.01
    itate
    1.00
    ceive
    0.99
    ulates
    0.99
    Activations Density 0.301%

    No Known Activations