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. 307
    Prev
    Next
    INDEX
    Explanations

    instances of the word "warm" and its variations, indicating a focus on warmth or positive sentiment

    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
     Sessions
    -0.70
     Continued
    -0.68
    ryu
    -0.66
     slic
    -0.65
     Macron
    -0.65
    RFC
    -0.64
     Kenn
    -0.63
     lineback
    -0.63
     shred
    -0.62
     Flynn
    -0.62
    POSITIVE LOGITS
    Austral
    0.79
    ancies
    0.73
    iquid
    0.72
    ochemistry
    0.68
    ochem
    0.67
    otal
    0.66
    acting
    0.65
    CEO
    0.64
    asia
    0.63
    atos
    0.63
    Activations Density 0.031%

    No Known Activations