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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1350
    Prev
    Next
    INDEX
    Explanations

    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
    ingly
    -0.73
    �
    -0.69
    fully
    -0.67
    ̶
    -0.67
    �
    -0.66
    weekly
    -0.65
    �
    -0.64
    �
    -0.64
    �
    -0.64
    ��
    -0.63
    POSITIVE LOGITS
     Winc
    0.80
     McCull
    0.68
     coerc
    0.65
    tions
    0.63
     Doodle
    0.62
    orsi
    0.59
     Topic
    0.59
     horizont
    0.59
     Dup
    0.59
     Kus
    0.59
    Activations Density 0.130%

    No Known Activations