© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 899
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods, indicating 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
    acus
    -0.81
    owitz
    -0.68
     guiActiveUn
    -0.66
    ivari
    -0.66
    gorith
    -0.65
     annex
    -0.65
    obiles
    -0.64
    ters
    -0.63
    aries
    -0.63
    ット
    -0.62
    POSITIVE LOGITS
    mind
    0.71
     impression
    0.64
    mast
    0.64
    sense
    0.62
     affection
    0.62
    battle
    0.62
     remembrance
    0.61
    30
    0.60
    holder
    0.58
     disappointment
    0.58
    Activations Density 0.029%

    No Known Activations