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. 169
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptions of product features

    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
    andi
    -0.80
    rx
    -0.78
    BER
    -0.77
    Topics
    -0.75
    HQ
    -0.74
    furt
    -0.71
    DEN
    -0.70
    lav
    -0.69
    shi
    -0.68
    stad
    -0.67
    POSITIVE LOGITS
     instrument
    0.69
     microphone
    0.65
     Morse
    0.63
     all
    0.63
     adjustable
    0.61
     heating
    0.60
     hostage
    0.60
    aith
    0.60
     tether
    0.60
     immunity
    0.60
    Activations Density 0.073%

    No Known Activations