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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1686
    Prev
    Next
    INDEX
    Explanations

    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
    ruck
    -0.66
    rieved
    -0.66
    paralle
    -0.66
    minist
    -0.65
    reau
    -0.64
    vier
    -0.64
    riad
    -0.63
    raq
    -0.62
    redits
    -0.59
    bons
    -0.59
    POSITIVE LOGITS
    apo
    0.67
    inventoryQuantity
    0.61
     TIME
    0.60
    stars
    0.59
    oided
    0.58
     age
    0.58
     Answer
    0.57
     speak
    0.56
     advise
    0.55
     Autob
    0.54
    Activations Density 0.069%

    No Known Activations