© 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. 1109
    Prev
    Next
    INDEX
    Explanations

    items or entities listed in a sequential or comparatory context

    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
    doms
    -0.73
    bara
    -0.72
    ogun
    -0.72
    hyde
    -0.69
    invoke
    -0.68
    usters
    -0.67
    inx
    -0.67
    覚醒
    -0.66
    xual
    -0.66
    keyes
    -0.66
    POSITIVE LOGITS
     Cosponsors
    0.76
     Guid
    0.68
     Por
    0.60
     Conversion
    0.59
     Prop
    0.59
     Federal
    0.58
     Num
    0.58
     Judicial
    0.57
     Ful
    0.57
     Bethlehem
    0.57
    Activations Density 0.113%

    No Known Activations