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. 397
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" and variations in capitalization

    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
    isons
    -0.78
     appeals
    -0.74
    opsy
    -0.74
    izons
    -0.73
     searches
    -0.73
    itle
    -0.73
    irtual
    -0.72
     qualifies
    -0.71
    rency
    -0.71
    iries
    -0.71
    POSITIVE LOGITS
     Clown
    0.79
     Jolly
    0.73
     Throne
    0.69
     Shutterstock
    0.67
     Chronicle
    0.67
     Mighty
    0.66
     Castle
    0.65
     Celt
    0.62
     Brief
    0.61
     Plain
    0.61
    Activations Density 0.108%

    No Known Activations