Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 344
    Prev
    Next
    INDEX
    Explanations

    references to objects or concepts associated with hands

    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
     disappoint
    -0.68
     disapp
    -0.67
     enigmatic
    -0.60
    onymous
    -0.59
     derog
    -0.58
     reciproc
    -0.58
     accomp
    -0.56
    rs
    -0.56
    abby
    -0.53
     deletion
    -0.52
    POSITIVE LOGITS
    eye
    0.80
    held
    0.75
    illin
    0.71
    gren
    0.70
    heed
    0.69
    written
    0.68
    gang
    0.67
    cart
    0.67
    Cam
    0.65
    rate
    0.63
    Activations Density 0.020%

    No Known Activations