© 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. 1060
    Prev
    Next
    INDEX
    Explanations

    words related to comments and commentary

    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
    inventoryQuantity
    -0.85
    natureconservancy
    -0.78
    eren
    -0.74
    igne
    -0.72
    enegger
    -0.71
    Í
    -0.70
    rely
    -0.67
    ered
    -0.65
    avid
    -0.64
    aye
    -0.63
    POSITIVE LOGITS
     RX
    0.73
     Thread
    0.70
     Bleach
    0.68
    ollow
    0.68
     threads
    0.67
    usha
    0.64
     medium
    0.64
     Pixie
    0.64
     Ashes
    0.64
    below
    0.63
    Activations Density 0.086%

    No Known Activations