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. 1-TRES-DC
    5. 4018
    Prev
    Next
    INDEX
    Explanations

    references to political leaders and their titles

    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
    Enlarge
    -0.83
    gur
    -0.82
    DragonMagazine
    -0.72
    hra
    -0.68
    raviolet
    -0.68
    media
    -0.67
    tel
    -0.66
    hw
    -0.66
    ertodd
    -0.65
    rared
    -0.65
    POSITIVE LOGITS
     Despair
    0.68
     Herbert
    0.66
    ial
    0.66
     Goose
    0.63
     Dust
    0.63
    =-=-=-=-
    0.63
    ipop
    0.61
     Forrest
    0.60
     Seymour
    0.60
     Rampage
    0.60
    Activations Density 0.042%

    No Known Activations