© 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. 1830
    Prev
    Next
    INDEX
    Explanations

    variations of the word "engage."

    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
     bast
    -0.69
     excel
    -0.64
    istical
    -0.63
     horns
    -0.60
     marsh
    -0.59
    yright
    -0.58
     cass
    -0.58
     rh
    -0.58
    igon
    -0.58
     dotted
    -0.58
    POSITIVE LOGITS
    len
    0.87
    odder
    0.79
    RF
    0.78
    AGE
    0.73
    ryn
    0.73
    lished
    0.72
    sect
    0.71
    low
    0.71
    loss
    0.71
    elsius
    0.68
    Activations Density 0.018%

    No Known Activations