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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 309
    Prev
    Next
    INDEX
    Explanations

    accomplishments and professional roles of individuals

    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
    Known
    -0.70
    Reviewed
    -0.66
    Controller
    -0.65
    Years
    -0.63
    Ranked
    -0.63
    Else
    -0.62
     Contains
    -0.61
    gha
    -0.61
    boss
    -0.60
    hoff
    -0.60
    POSITIVE LOGITS
     privat
    0.66
    izophren
    0.63
     humanitarian
    0.63
     pige
    0.60
    fal
    0.59
     salv
    0.58
    uilding
    0.57
    olding
    0.57
     sinners
    0.57
     helicopters
    0.56
    Activations Density 0.380%

    No Known Activations