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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 396
    Prev
    Next
    INDEX
    Explanations

    references to surnames and last names

    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
    igon
    -0.78
    cko
    -0.74
    seys
    -0.72
    Plex
    -0.70
    ifax
    -0.69
    kowski
    -0.69
    airo
    -0.67
    ipeg
    -0.67
    essee
    -0.67
    zin
    -0.66
    POSITIVE LOGITS
     scenes
    0.72
    �
    0.69
     scene
    0.68
    い
    0.66
    eries
    0.65
     Hud
    0.65
     Offense
    0.64
     liberty
    0.63
    Narr
    0.60
     racket
    0.60
    Activations Density 1.174%

    No Known Activations