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. 28
    Prev
    Next
    INDEX
    Explanations

    repetitive concepts and actions

    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
    foundland
    -0.62
     incl
    -0.61
     facult
    -0.61
    20439
    -0.60
    iosyncr
    -0.58
    ppo
    -0.58
    ife
    -0.57
    ][/
    -0.57
    osi
    -0.57
     Zeit
    -0.57
    POSITIVE LOGITS
    sung
    0.77
     AS
    0.63
     LAPD
    0.59
    otin
    0.59
    monds
    0.58
     Myanmar
    0.58
    growth
    0.57
    prises
    0.56
     UC
    0.55
    vati
    0.55
    Activations Density 0.057%

    No Known Activations