© 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. 2746
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and quotes

    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
     culminated
    -0.58
     highlighted
    -0.56
    orie
    -0.56
     turnover
    -0.55
    urring
    -0.54
     flagged
    -0.54
     stresses
    -0.54
     indexed
    -0.53
     points
    -0.53
     blasted
    -0.53
    POSITIVE LOGITS
    Cause
    0.78
    emet
    0.68
    Deal
    0.68
    Brother
    0.66
    greg
    0.66
    Were
    0.66
    Middle
    0.66
    Machine
    0.65
    Gy
    0.64
    sle
    0.63
    Activations Density 0.043%

    No Known Activations