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. 335
    Prev
    Next
    INDEX
    Explanations

    punctuations, particularly periods at the end of sentences

    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
    oku
    -0.71
    ��
    -0.69
     overboard
    -0.69
    estamp
    -0.64
    iances
    -0.64
    atories
    -0.64
    oma
    -0.63
     nightly
    -0.62
    gling
    -0.62
    icus
    -0.62
    POSITIVE LOGITS
    田
    0.79
    Benz
    0.77
    Emer
    0.76
    ospons
    0.72
    Reloaded
    0.72
    TYPE
    0.71
    Fill
    0.71
     cumbers
    0.70
    escal
    0.69
    JD
    0.69
    Activations Density 0.015%

    No Known Activations