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. 121
    Prev
    Next
    INDEX
    Explanations

    closing punctuation marks, specifically brackets and parentheses

    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
    Against
    -0.74
    Nap
    -0.69
    con
    -0.67
    witch
    -0.63
    ORE
    -0.61
    Constructed
    -0.60
    "-
    -0.60
    pop
    -0.60
    Prem
    -0.60
    "…
    -0.59
    POSITIVE LOGITS
    ��
    0.80
    xual
    0.74
     Samar
    0.74
    ��
    0.68
    nesday
    0.66
    ernel
    0.65
    ���
    0.65
     Volunteers
    0.63
    iggs
    0.63
    retty
    0.62
    Activations Density 0.141%

    No Known Activations