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. 163
    Prev
    Next
    INDEX
    Explanations

    occurrences of the plural form of a noun

    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
     sacrific
    -0.64
     Sci
    -0.61
     contrace
    -0.61
     hither
    -0.61
     proposition
    -0.60
    rama
    -0.60
     Cruiser
    -0.58
     Herod
    -0.58
     Ottoman
    -0.57
     disadvant
    -0.56
    POSITIVE LOGITS
    keleton
    1.00
    leeve
    0.96
    ixty
    0.96
    uggest
    0.95
    iblings
    0.95
    atisf
    0.92
    ptions
    0.91
    ouls
    0.91
    istance
    0.90
    ket
    0.88
    Activations Density 0.102%

    No Known Activations