© 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. 3116
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "add a" followed by various nouns

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    0200
    -0.69
     Protesters
    -0.69
    alli
    -0.69
     outdoors
    -0.63
    rano
    -0.62
    sburg
    -0.58
    dayName
    -0.58
    RT
    -0.58
    姫
    -0.58
    PsyNetMessage
    -0.56
    POSITIVE LOGITS
     certific
    0.68
     describ
    0.67
    gment
    0.66
     reflective
    0.65
     informational
    0.65
     microscopic
    0.62
     dimensional
    0.62
    gotten
    0.61
    DEBUG
    0.60
     deleted
    0.59
    Activations Density 0.174%

    No Known Activations