© 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. 2844
    Prev
    Next
    INDEX
    Explanations

    scenarios that involve decision-making and personal responsibility

    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
     arrang
    -0.69
    lier
    -0.68
    HER
    -0.68
    FUL
    -0.66
     suprem
    -0.66
     thereof
    -0.65
     targ
    -0.65
    geries
    -0.64
     occas
    -0.62
    Whe
    -0.61
    POSITIVE LOGITS
    atech
    0.80
    otics
    0.67
    edin
    0.66
    ouple
    0.66
    alla
    0.65
    agine
    0.64
    eto
    0.64
    imate
    0.63
    oran
    0.62
    otin
    0.62
    Activations Density 0.317%

    No Known Activations