© 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. 1398
    Prev
    Next
    INDEX
    Explanations

    terms related to demographics and community ownership

    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
    asking
    -0.83
    anchester
    -0.79
    given
    -0.75
    UG
    -0.73
    ntil
    -0.73
    ogue
    -0.70
    shown
    -0.70
     Palest
    -0.67
    alias
    -0.67
    roxy
    -0.66
    POSITIVE LOGITS
     compet
    0.89
     inhabit
    0.88
     negoti
    0.88
     loves
    0.88
     likes
    0.86
     excel
    0.85
     resists
    0.84
     collects
    0.84
     wishes
    0.84
     accum
    0.84
    Activations Density 0.429%

    No Known Activations