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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 573
    Prev
    Next
    INDEX
    Explanations

    prominent names or titles related to institutions and organizations

    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
    istance
    -0.58
    urnal
    -0.56
    proc
    -0.55
    dependent
    -0.53
    incre
    -0.53
    transform
    -0.51
    hemer
    -0.50
    etermin
    -0.50
    lves
    -0.50
    itiz
    -0.50
    POSITIVE LOGITS
     Views
    0.59
     UKIP
    0.58
     Alberta
    0.57
     Silk
    0.53
     Ernst
    0.52
     charism
    0.51
    osate
    0.51
     Brisbane
    0.51
     Milan
    0.50
     Calgary
    0.50
    Activations Density 1.668%

    No Known Activations