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. 118
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in various forms

    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
    strike
    -0.67
    Lind
    -0.66
    oire
    -0.64
    riz
    -0.63
    nder
    -0.62
     ‎
    -0.62
    ć
    -0.62
    henko
    -0.61
    luence
    -0.61
    ‑
    -0.61
    POSITIVE LOGITS
     adversaries
    0.74
    ���
    0.73
    icons
    0.72
     attackers
    0.72
     enemies
    0.71
     millenn
    0.70
     indistinguishable
    0.69
    agles
    0.68
    friends
    0.67
     heroes
    0.66
    Activations Density 0.151%

    No Known Activations