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. 129
    Prev
    Next
    INDEX
    Explanations

    references to past actions or events

    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
    thinkable
    -0.77
    ances
    -0.67
    axter
    -0.64
    wolves
    -0.64
    isSpecialOrderable
    -0.63
    Hope
    -0.62
     Cloak
    -0.61
    WAYS
    -0.61
     thefts
    -0.61
     Juda
    -0.61
    POSITIVE LOGITS
     showed
    0.71
     blew
    0.68
     sparked
    0.66
     flashed
    0.65
     started
    0.63
     grace
    0.63
     briefly
    0.63
    istrates
    0.62
     first
    0.61
     wore
    0.59
    Activations Density 0.136%

    No Known Activations