© 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. 2799
    Prev
    Next
    INDEX
    Explanations

    the phrase "didn't" 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
     exha
    -0.77
    anwhile
    -0.72
     withd
    -0.72
     drained
    -0.70
     elsewhere
    -0.62
     fulfilled
    -0.62
     orderly
    -0.61
     Cance
    -0.60
     succeed
    -0.60
     treadmill
    -0.59
    POSITIVE LOGITS
    't
    1.07
    uts
    0.79
    í
    0.75
    fell
    0.69
    eness
    0.68
    ad
    0.66
    ´
    0.65
    ivers
    0.65
    ut
    0.65
    upper
    0.64
    Activations Density 0.097%

    No Known Activations