© 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. 1253
    Prev
    Next
    INDEX
    Explanations

    personal possessive expressions regarding favorites and preferences

    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
    orks
    -0.97
    ilater
    -0.90
    aceous
    -0.85
    margin
    -0.76
    icult
    -0.76
    ipples
    -0.76
    iaz
    -0.75
    lio
    -0.75
    oppable
    -0.75
    tnc
    -0.75
    POSITIVE LOGITS
     favorite
    0.94
     favourite
    0.89
     fav
    0.86
     goodbye
    0.77
     preference
    0.77
     Favorite
    0.68
     fault
    0.67
     gri
    0.65
    Favorite
    0.65
     preferred
    0.64
    Activations Density 0.042%

    No Known Activations