© 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. 528
    Prev
    Next
    INDEX
    Explanations

    references to the concept of benefits and advantages

    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
    olon
    -0.66
    Introduced
    -0.66
    +=
    -0.65
    owicz
    -0.63
    SPONSORED
    -0.63
    llah
    -0.62
    isms
    -0.62
    iop
    -0.62
    involved
    -0.62
    ****************
    -0.61
    POSITIVE LOGITS
     tremend
    0.80
     immensely
    0.77
     enormously
    0.72
     aest
    0.68
     perverse
    0.67
     tremendously
    0.67
     carbohyd
    0.63
     estimating
    0.62
     fant
    0.62
     handsome
    0.61
    Activations Density 0.050%

    No Known Activations