© 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. 1469
    Prev
    Next
    INDEX
    Explanations

    the word "especially" indicating significant emphasis or importance

    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
    gdala
    -0.93
    ァ
    -0.79
    abit
    -0.69
    swick
    -0.69
    bent
    -0.66
    sharp
    -0.63
    finder
    -0.63
    Goal
    -0.61
    kj
    -0.58
    insert
    -0.58
    POSITIVE LOGITS
     when
    0.78
     since
    0.73
     if
    0.64
    iens
    0.60
    ér
    0.60
     during
    0.59
     concerning
    0.59
    when
    0.58
     BY
    0.58
    ibo
    0.58
    Activations Density 0.030%

    No Known Activations