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. 60
    Prev
    Next
    INDEX
    Explanations

    phrases related to examining or investigating something in detail

    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
    artney
    -0.76
     gravy
    -0.76
    assic
    -0.72
    ubb
    -0.71
    ullivan
    -0.68
    olson
    -0.68
    hma
    -0.67
    uous
    -0.67
    ertodd
    -0.66
     tatt
    -0.66
    POSITIVE LOGITS
    hold
    0.62
    ˜
    0.60
     Patrol
    0.59
     Strike
    0.57
    Grab
    0.57
     Drift
    0.57
    onomy
    0.57
     however
    0.57
    antically
    0.56
    ITCH
    0.56
    Activations Density 0.102%

    No Known Activations