© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 905
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" in various contexts

    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
    abouts
    -0.86
    ax
    -0.77
    akers
    -0.76
    liga
    -0.76
    ng
    -0.74
    Morning
    -0.73
    yt
    -0.73
    ˈ
    -0.73
    anka
    -0.72
    rir
    -0.72
    POSITIVE LOGITS
     vice
    0.99
     director
    0.97
     chief
    0.91
     managing
    0.89
     superintendent
    0.86
     head
    0.85
     keynote
    0.85
     Director
    0.84
     chairman
    0.83
     chair
    0.80
    Activations Density 0.047%

    No Known Activations