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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 435
    Prev
    Next
    INDEX
    Explanations

    expressions indicating concession or contrast

    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
     otherwise
    -0.71
     disapp
    -0.70
    iability
    -0.69
     Otherwise
    -0.69
    conom
    -0.66
    Otherwise
    -0.65
    ":"/
    -0.64
    buster
    -0.64
    COMPLE
    -0.63
    shall
    -0.62
    POSITIVE LOGITS
    interstitial
    0.93
     companies
    0.63
     conspicuous
    0.61
     thousands
    0.60
     multim
    0.60
     hardware
    0.59
    phy
    0.57
     products
    0.57
     hundreds
    0.56
     gangs
    0.56
    Activations Density 0.034%

    No Known Activations