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. 12
    Prev
    Next
    INDEX
    Explanations

    the preposition "at" and its associated numeric values indicating intensity or frequency

    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
    artifacts
    -0.72
    artisan
    -0.71
    GN
    -0.64
     AUTH
    -0.64
    Mah
    -0.63
    nance
    -0.62
    atically
    -0.57
    enda
    -0.56
    acies
    -0.56
    nect
    -0.56
    POSITIVE LOGITS
     times
    0.78
    oling
    0.75
     odds
    0.72
     hrs
    0.70
    ornings
    0.67
    inctions
    0.67
     ende
    0.66
     lightning
    0.65
     variance
    0.65
     intervals
    0.65
    Activations Density 0.090%

    No Known Activations