© 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. 1628
    Prev
    Next
    INDEX
    Explanations

    the word "said" 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
    Downloadha
    -0.74
    ibly
    -0.71
    eele
    -0.69
    pmwiki
    -0.67
    ilib
    -0.67
    ortal
    -0.67
    olesterol
    -0.67
    士
    -0.66
    PsyNetMessage
    -0.64
    negie
    -0.63
    POSITIVE LOGITS
     none
    0.74
     {"
    0.65
     Rampage
    0.64
    soever
    0.63
    leanor
    0.62
     Applicant
    0.59
    nin
    0.59
     Conversation
    0.59
     Sard
    0.57
     enthusi
    0.57
    Activations Density 0.091%

    No Known Activations