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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 976
    Prev
    Next
    INDEX
    Explanations

    verbs related to the act of bringing or introducing something

    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
    Govern
    -0.72
    gging
    -0.72
    potion
    -0.69
    aker
    -0.68
    mouth
    -0.68
    ovable
    -0.68
    osate
    -0.67
     sqor
    -0.67
    god
    -0.67
    yet
    -0.67
    POSITIVE LOGITS
     forward
    0.67
     Twin
    0.64
     back
    0.60
     acknowledgement
    0.60
     uphill
    0.59
     forth
    0.59
     along
    0.59
     filler
    0.58
    inav
    0.58
     Sunrise
    0.58
    Activations Density 0.020%

    No Known Activations