Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 138
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the word "I'm" or its variations in different 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
    iHUD
    -0.81
     Immunity
    -0.68
    enges
    -0.65
    ties
    -0.65
    apper
    -0.65
    worthiness
    -0.62
     SetTextColor
    -0.61
    \">
    -0.61
    itters
    -0.60
     valves
    -0.60
    POSITIVE LOGITS
     glad
    0.94
     unable
    0.91
     ashamed
    0.88
     proud
    0.87
     thankful
    0.86
     addicted
    0.86
     pleased
    0.82
     grateful
    0.80
     indebted
    0.79
     willing
    0.79
    Activations Density 0.025%

    No Known Activations