© 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. 1587
    Prev
    Next
    INDEX
    Explanations

    verbs indicating states of being or actions related to subjects in a narrative context

    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
     amuse
    -0.73
     avoidance
    -0.69
     DL
    -0.69
     retire
    -0.67
     embarrassing
    -0.66
     savings
    -0.66
     disappear
    -0.65
     inherit
    -0.64
     oust
    -0.63
     escape
    -0.63
    POSITIVE LOGITS
    orc
    0.85
    our
    0.82
    eval
    0.77
    ascript
    0.74
    igor
    0.74
    YC
    0.72
    kell
    0.72
    ragon
    0.71
    uran
    0.71
    RH
    0.70
    Activations Density 0.350%

    No Known Activations