© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3125
    Prev
    Next
    INDEX
    Explanations

    instances of the word "demonstrate" and its variations, indicating evidence or proof of concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ater
    -0.86
    inventoryQuantity
    -0.80
    enda
    -0.79
    soDeliveryDate
    -0.79
    abilia
    -0.78
    apter
    -0.77
    DragonMagazine
    -0.76
    ATER
    -0.76
    heimer
    -0.74
    DA
    -0.74
    POSITIVE LOGITS
     how
    0.67
     Beg
    0.65
     why
    0.62
     Norn
    0.61
    peer
    0.61
     IPCC
    0.60
     bloom
    0.59
    ku
    0.58
     Brun
    0.58
     anew
    0.57
    Activations Density 0.078%

    No Known Activations