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. 166
    Prev
    Next
    INDEX
    Explanations

    dates in November

    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
    ーテ
    -0.82
    イト
    -0.76
    フォ
    -0.74
    OPLE
    -0.71
    enegger
    -0.69
    NRS
    -0.67
    aimon
    -0.67
    アル
    -0.66
    GMT
    -0.66
    GROUP
    -0.66
    POSITIVE LOGITS
    abal
    0.62
    peat
    0.60
     Jolly
    0.60
    alty
    0.60
     Lup
    0.58
    mbol
    0.56
     weep
    0.55
     bout
    0.55
     fringe
    0.54
     bleed
    0.53
    Activations Density 0.028%

    No Known Activations