© 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. 2945
    Prev
    Next
    INDEX
    Explanations

    the repetition of the verb "was" 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
    tera
    -0.68
     extraord
    -0.67
    mare
    -0.66
     copies
    -0.65
    iku
    -0.64
    inav
    -0.64
    ottage
    -0.64
     Seym
    -0.63
    ativity
    -0.62
    miss
    -0.62
    POSITIVE LOGITS
     carrying
    0.73
     partying
    0.72
     smoking
    0.69
     texting
    0.67
     shaking
    0.67
     Flavoring
    0.66
     repairing
    0.65
     celebrating
    0.64
     biking
    0.64
     waiting
    0.64
    Activations Density 0.132%

    No Known Activations