© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 583
    Prev
    Next
    INDEX
    Explanations

    possessive forms indicating identity or relationship

    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
    uates
    -0.83
    inges
    -0.78
    forts
    -0.72
     confines
    -0.71
    abba
    -0.69
    %%%%
    -0.69
    obo
    -0.68
    awks
    -0.68
    lehem
    -0.67
    urches
    -0.65
    POSITIVE LOGITS
     been
    1.28
     gotten
    1.20
    been
    1.05
     grown
    0.98
     gone
    0.94
     fallen
    0.94
     done
    0.92
     undergone
    0.90
     Been
    0.87
     withdrawn
    0.87
    Activations Density 0.076%

    No Known Activations