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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2424
    Prev
    Next
    INDEX
    Explanations

    expressions indicating information transmission or reporting from sources

    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
    ウス
    -0.80
    Appearances
    -0.75
    �士
    -0.74
    foreseen
    -0.69
    population
    -0.68
    SPONSORED
    -0.67
     incent
    -0.67
    ilda
    -0.64
     secondly
    -0.63
    vity
    -0.62
    POSITIVE LOGITS
     Scroll
    0.75
     PubMed
    0.71
    Downloadha
    0.71
     Rolling
    0.69
     Yon
    0.69
     Oak
    0.66
     Monkey
    0.63
     Clean
    0.63
     FT
    0.62
     Lap
    0.62
    Activations Density 0.026%

    No Known Activations