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. 9-TRES-DC
    5. 618
    Prev
    Next
    INDEX
    Explanations

    references to characters and plot points from various fictional narratives

    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
    Reviewed
    -0.80
    RAW
    -0.72
    Edited
    -0.71
    kson
    -0.70
     deliber
    -0.68
    reviewed
    -0.66
    rieved
    -0.65
    aminer
    -0.64
    schild
    -0.63
    nih
    -0.63
    POSITIVE LOGITS
     Legends
    0.83
    assic
    0.79
     franchise
    0.78
    Legend
    0.78
    atre
    0.77
     novels
    0.75
     Invaders
    0.74
     Rings
    0.73
     FF
    0.71
     film
    0.71
    Activations Density 0.486%

    No Known Activations