Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 299
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their occurrences in various contexts

    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
     vain
    -0.84
     equally
    -0.80
     similarly
    -0.80
     broadly
    -0.74
     densely
    -0.72
     meanwhile
    -0.72
     Ferry
    -0.71
     brave
    -0.71
     previously
    -0.70
     polled
    -0.70
    POSITIVE LOGITS
    Returns
    1.21
    Reviewer
    1.20
    Contents
    1.16
    Instruct
    1.15
    Mot
    1.14
    Layout
    1.14
    Parameters
    1.14
    Characters
    1.13
    Example
    1.12
    Development
    1.12
    Activations Density 0.224%

    No Known Activations