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. 100
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation, specifically 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
     shoulders
    -0.73
    gaard
    -0.61
     shoulder
    -0.60
     spons
    -0.59
     booth
    -0.59
    orthern
    -0.57
     gru
    -0.57
    orie
    -0.56
     sep
    -0.56
    iss
    -0.56
    POSITIVE LOGITS
    Compat
    0.80
    PRES
    0.78
    TPP
    0.70
    Parents
    0.70
    Experience
    0.68
    Doctor
    0.67
    Mech
    0.64
    VEL
    0.64
    ���
    0.64
    Sometimes
    0.64
    Activations Density 0.020%

    No Known Activations