© 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. 1939
    Prev
    Next
    INDEX
    Explanations

    the phrase "full of" followed by various descriptors or attributes

    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
     Appears
    -0.83
     Loving
    -0.72
    quet
    -0.72
    orthy
    -0.71
    iw
    -0.71
    raised
    -0.71
    teenth
    -0.70
    aneers
    -0.69
    omever
    -0.69
    treated
    -0.67
    POSITIVE LOGITS
     frustrations
    0.92
     inconsistencies
    0.89
     irony
    0.87
     optimism
    0.87
     complexities
    0.86
     distractions
    0.86
     positives
    0.86
     negativity
    0.85
     controversies
    0.84
     pitfalls
    0.83
    Activations Density 0.210%

    No Known Activations