© 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. 1367
    Prev
    Next
    INDEX
    Explanations

    expressions of anticipation or future events

    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
    argo
    -0.63
    ioned
    -0.61
    rup
    -0.61
    wik
    -0.60
    kees
    -0.60
    ees
    -0.59
    emis
    -0.58
    aby
    -0.58
    ajo
    -0.58
    gap
    -0.57
    POSITIVE LOGITS
    UTH
    0.67
     inherit
    0.67
    essage
    0.63
    ullivan
    0.63
    resents
    0.62
    reference
    0.56
    カ
    0.56
    ザ
    0.56
    ournal
    0.56
     largeDownload
    0.56
    Activations Density 1.405%

    No Known Activations