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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 330
    Prev
    Next
    INDEX
    Explanations

    mentions of the letter "J" followed by numbers, indicating a focus on geographical or political locations

    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
     Flore
    -0.67
     Giul
    -0.64
    lein
    -0.63
    ../
    -0.62
    names
    -0.61
     Engel
    -0.61
     JC
    -0.59
    Frameworks
    -0.58
     Jerry
    -0.57
     Jian
    -0.57
    POSITIVE LOGITS
    owl
    0.81
    omo
    0.76
    ungle
    0.74
    ugal
    0.73
    etheless
    0.72
    olla
    0.70
    ive
    0.69
    hang
    0.68
    ug
    0.67
    odo
    0.66
    Activations Density 0.024%

    No Known Activations