© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2599
    Prev
    Next
    INDEX
    Explanations

    negative phrasing or expressions of uncertainty

    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
    immer
    -0.73
    ィ
    -0.67
    uchin
    -0.67
    ints
    -0.65
    isance
    -0.64
    ggles
    -0.64
    aneers
    -0.64
    iencies
    -0.63
    anship
    -0.62
    ython
    -0.61
    POSITIVE LOGITS
     ashamed
    0.99
     bothered
    0.93
     intimidated
    0.93
     thrilled
    0.90
     pleased
    0.85
     concerned
    0.84
     impressed
    0.84
     interested
    0.83
     surprised
    0.80
     alarmed
    0.80
    Activations Density 0.097%

    No Known Activations