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. 332
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as" in various contexts

    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
    ーテ
    -0.67
    illary
    -0.66
    ALLY
    -0.64
    INAL
    -0.63
    orical
    -0.62
     Advent
    -0.60
     Prelude
    -0.60
    tenance
    -0.60
     nursery
    -0.60
    Intern
    -0.59
    POSITIVE LOGITS
     expected
    0.87
    ahi
    0.85
     anticipated
    0.80
     envisioned
    0.78
     hoped
    0.77
    pect
    0.77
     planned
    0.76
    pects
    0.75
    wat
    0.72
     envis
    0.70
    Activations Density 0.088%

    No Known Activations