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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 51
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or function

    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
    isi
    -0.81
    ategory
    -0.79
    chan
    -0.75
    akings
    -0.75
    anamo
    -0.75
    oder
    -0.75
    RIPT
    -0.71
    etta
    -0.71
    azo
    -0.71
    HCR
    -0.71
    POSITIVE LOGITS
     coordinated
    0.78
     unanimous
    0.75
     accurate
    0.70
     contraction
    0.68
     careful
    0.68
     graceful
    0.67
     upward
    0.67
     rapid
    0.67
     orderly
    0.67
     downward
    0.66
    Activations Density 0.107%

    No Known Activations