© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1328
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "may" in various contexts

    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
    ATED
    -0.71
    CLASSIFIED
    -0.71
    ATES
    -0.70
    ancies
    -0.70
    IDES
    -0.69
    Fine
    -0.68
     mathemat
    -0.67
    foreseen
    -0.66
    thinkable
    -0.65
    enses
    -0.64
    POSITIVE LOGITS
    hap
    0.93
    haps
    0.84
    onna
    0.75
    hof
    0.71
     Allah
    0.70
    flies
    0.68
     1944
    0.67
    orsche
    0.66
    liam
    0.66
     1942
    0.65
    Activations Density 0.040%

    No Known Activations