© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 506
    Prev
    Next
    INDEX
    Explanations

    aspects related to physical interaction or manipulation of objects

    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
    wcsstore
    -0.68
    lied
    -0.60
     predic
    -0.60
    ashington
    -0.60
    express
    -0.58
    20439
    -0.58
    eq
    -0.58
     predec
    -0.57
    mask
    -0.57
     subscribe
    -0.57
    POSITIVE LOGITS
     them
    1.15
     him
    1.01
     THEM
    0.95
     us
    0.91
     it
    0.90
     everyone
    0.90
     everything
    0.90
     your
    0.88
     everybody
    0.88
     Them
    0.87
    Activations Density 1.166%

    No Known Activations