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. 141
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "just one example of."

    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
    \\\\\\\\
    -0.77
     adolesc
    -0.67
     recomm
    -0.67
    OWS
    -0.66
    baugh
    -0.65
    ��
    -0.65
     Hayden
    -0.65
    owed
    -0.64
    ANE
    -0.60
     tatt
    -0.60
    POSITIVE LOGITS
    lev
    0.75
    low
    0.66
    ⓘ
    0.63
    rab
    0.63
    ロ
    0.61
    assemb
    0.61
     Explosive
    0.60
     low
    0.60
    lean
    0.60
    eele
    0.59
    Activations Density 0.021%

    No Known Activations