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. 372
    Prev
    Next
    INDEX
    Explanations

    variations of the word "entertain" or related terms

    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
    sworth
    -0.75
    luster
    -0.73
    nery
    -0.72
    ively
    -0.66
    adium
    -0.65
    assetsadobe
    -0.63
    sett
    -0.63
    ufact
    -0.62
    fulness
    -0.62
    ners
    -0.60
    POSITIVE LOGITS
    ires
    0.84
    ire
    0.82
    ropy
    0.82
    IRE
    0.81
    angles
    0.75
    rag
    0.74
    soDeliveryDate
    0.73
    ribe
    0.73
    irez
    0.71
    reb
    0.71
    Activations Density 0.017%

    No Known Activations