© 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. 1521
    Prev
    Next
    INDEX
    Explanations

    the word "Ultimately" along with contextual discussions of conclusions or final points

    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
     proble
    -0.85
    sein
    -0.78
    agi
    -0.72
    agame
    -0.72
    iqueness
    -0.69
    Seg
    -0.69
    uum
    -0.69
    clave
    -0.69
    =-=-
    -0.67
    ickr
    -0.67
    POSITIVE LOGITS
     watering
    0.66
     aim
    0.65
     Mens
    0.65
     Aim
    0.63
     prescription
    0.60
     Tooth
    0.60
     aiding
    0.60
     vengeance
    0.60
     it
    0.59
     Brav
    0.59
    Activations Density 0.042%

    No Known Activations