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. 251
    Prev
    Next
    INDEX
    Explanations

    actionable advice related to personal development and decision-making

    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
     [+
    -0.68
    [/
    -0.68
    wise
    -0.64
     [/
    -0.63
    conom
    -0.62
     Gore
    -0.62
     Skydragon
    -0.61
    falls
    -0.61
    ktop
    -0.60
    cephal
    -0.59
    POSITIVE LOGITS
     yourself
    1.02
     your
    0.89
     yourselves
    0.78
     Yourself
    0.74
     them
    0.74
    them
    0.72
    your
    0.72
     THEM
    0.68
     COURT
    0.67
     YOUR
    0.65
    Activations Density 0.488%

    No Known Activations