© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1072
    Prev
    Next
    INDEX
    Explanations

    instances of the word "we" indicating collective action or sentiment

    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
    photos
    -0.65
    fulness
    -0.57
    cum
    -0.55
     persists
    -0.55
     Photos
    -0.55
     arises
    -0.54
    item
    -0.54
    comes
    -0.52
     contrary
    -0.52
    leeve
    -0.51
    POSITIVE LOGITS
    asel
    0.85
    ird
    0.77
    Mos
    0.72
    Sov
    0.71
    imar
    0.68
    erd
    0.67
    akening
    0.67
    eks
    0.66
    bsite
    0.65
    eding
    0.64
    Activations Density 0.152%

    No Known Activations