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. 26
    Prev
    Next
    INDEX
    Explanations

    expressions of emotions and reactions

    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
    Sources
    -0.71
    Girls
    -0.71
    them
    -0.64
    rogens
    -0.64
    ynasty
    -0.62
     IMAGES
    -0.60
     Cities
    -0.60
     Orchestra
    -0.59
    Episode
    -0.58
    iseum
    -0.58
    POSITIVE LOGITS
    ided
    0.91
    iably
    0.83
    ifully
    0.82
    ained
    0.78
    viously
    0.78
    hand
    0.75
    staking
    0.75
    aining
    0.75
    sided
    0.74
    ently
    0.73
    Activations Density 0.232%

    No Known Activations