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. 25
    Prev
    Next
    INDEX
    Explanations

    references to specific events or actions related to information dissemination

    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
    nings
    -0.74
    hest
    -0.69
    vation
    -0.67
    ku
    -0.66
    below
    -0.65
    above
    -0.64
    hibit
    -0.64
    px
    -0.63
    rament
    -0.63
    tops
    -0.63
    POSITIVE LOGITS
     Pruitt
    0.79
     Nunes
    0.77
     Schumer
    0.62
     Julie
    0.60
     Pence
    0.58
     Nato
    0.58
    umsy
    0.57
    imsy
    0.57
     Volvo
    0.57
     Glover
    0.57
    Activations Density 0.306%

    No Known Activations