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. 144
    Prev
    Next
    INDEX
    Explanations

    phrases indicating clarification or redefinition

    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
    strength
    -0.69
    folio
    -0.68
    service
    -0.67
    Appearance
    -0.66
    screen
    -0.65
    cos
    -0.64
    ichick
    -0.64
    bat
    -0.64
    health
    -0.63
    factor
    -0.63
    POSITIVE LOGITS
    ettings
    0.62
     regards
    0.61
    joining
    0.60
     poses
    0.59
     confines
    0.57
     pse
    0.56
    aru
    0.56
     haun
    0.56
     mere
    0.55
     circles
    0.55
    Activations Density 0.056%

    No Known Activations