© 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. 1261
    Prev
    Next
    INDEX
    Explanations

    instances of the words "aboard" and "board," particularly in contexts related to transportation

    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
     acknow
    -0.88
     advoc
    -0.80
    ▬
    -0.74
     notch
    -0.71
     diplom
    -0.70
    ciating
    -0.68
     referral
    -0.68
    ドラゴン
    -0.67
     Commun
    -0.67
     recap
    -0.65
    POSITIVE LOGITS
    orph
    0.75
    hiba
    0.74
    BRE
    0.67
     Edwin
    0.67
    ritz
    0.65
    eddy
    0.64
    erous
    0.63
    hin
    0.62
    mage
    0.61
     Dough
    0.61
    Activations Density 0.073%

    No Known Activations