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. 14
    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
    ���
    -0.76
    galitarian
    -0.74
    mand
    -0.71
    udic
    -0.70
    Reviewed
    -0.66
    AIN
    -0.65
    sonian
    -0.65
    ÃÂ
    -0.64
    soever
    -0.64
     Requires
    -0.63
    POSITIVE LOGITS
     percentage
    1.03
     number
    1.00
     odds
    0.82
     total
    0.80
     proportion
    0.80
     share
    0.80
     probability
    0.76
     chance
    0.76
     ratio
    0.76
     decrease
    0.75
    Activations Density 0.248%

    No Known Activations