Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 266
    Prev
    Next
    INDEX
    Explanations

    numerical references, particularly the count of items

    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
    rating
    -0.87
    emi
    -0.86
    pee
    -0.82
    Appearances
    -0.77
    aired
    -0.77
    eating
    -0.76
    ultimate
    -0.73
    staking
    -0.72
    soDeliveryDate
    -0.71
    ridden
    -0.71
    POSITIVE LOGITS
     belts
    0.74
    xes
    0.74
     pieces
    0.73
     belt
    0.73
     tables
    0.72
     eras
    0.69
     spice
    0.68
     slices
    0.67
     divisions
    0.67
     pie
    0.67
    Activations Density 0.117%

    No Known Activations