© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 441
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as" indicating comparisons or descriptions

    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
    aska
    -0.64
     ASD
    -0.59
    ese
    -0.57
    number
    -0.57
    lot
    -0.57
    psey
    -0.56
    english
    -0.54
     understanding
    -0.54
    gin
    -0.54
    idth
    -0.53
    POSITIVE LOGITS
    icipated
    0.72
    natureconservancy
    0.71
    opped
    0.71
     mathemat
    0.67
    MIT
    0.66
    rowing
    0.65
    med
    0.63
    lighting
    0.62
    paio
    0.61
    idates
    0.61
    Activations Density 0.080%

    No Known Activations