© 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. 2726
    Prev
    Next
    INDEX
    Explanations

    titles and honorifics related to individuals

    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
     misunder
    -0.82
     thanked
    -0.71
     apologized
    -0.71
    exclusive
    -0.67
     unden
    -0.66
     mathemat
    -0.65
     thanking
    -0.65
     apologise
    -0.65
     apologizing
    -0.64
     toget
    -0.63
    POSITIVE LOGITS
    trak
    0.76
    uren
    0.71
    osity
    0.71
    icular
    0.71
    uries
    0.70
    arella
    0.69
    aeda
    0.69
    entimes
    0.69
    imeters
    0.68
    ield
    0.68
    Activations Density 0.076%

    No Known Activations