© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 642
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal opinions or reflections

    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
     endeav
    -0.66
    loads
    -0.62
    urat
    -0.61
    thur
    -0.61
    lessly
    -0.61
    cott
    -0.58
    lings
    -0.57
     scrimmage
    -0.57
    Hop
    -0.57
    transform
    -0.57
    POSITIVE LOGITS
    ahime
    0.62
     about
    0.61
     McCarthy
    0.60
    early
    0.59
    ancer
    0.58
     Approximately
    0.58
    enium
    0.58
     >>>
    0.58
    advertising
    0.57
    ater
    0.57
    Activations Density 0.364%

    No Known Activations