© 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. 2081
    Prev
    Next
    INDEX
    Explanations

    punctuation, specifically quotes and commas

    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
    rane
    -0.83
    vae
    -0.71
    iasis
    -0.71
     wart
    -0.69
    azard
    -0.67
    ileged
    -0.67
    gemony
    -0.67
    eus
    -0.66
    ailed
    -0.66
    ously
    -0.65
    POSITIVE LOGITS
    0002
    0.67
     implying
    0.65
    adding
    0.62
     foregoing
    0.60
     concluding
    0.59
    ICLE
    0.59
    1600
    0.57
    assuming
    0.57
     裏覚醒
    0.56
     although
    0.56
    Activations Density 0.175%

    No Known Activations