© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 421
    Prev
    Next
    INDEX
    Explanations

    mentions of the United States

    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
     undertaking
    -0.77
    igon
    -0.70
    rex
    -0.67
    ffect
    -0.65
    ourse
    -0.65
     htt
    -0.63
     administr
    -0.63
     interrogated
    -0.63
    training
    -0.63
     encountering
    -0.62
    POSITIVE LOGITS
    �
    0.68
     Fruit
    0.66
    :\
    0.65
    Sense
    0.64
    ら
    0.63
    Insert
    0.63
     Doodle
    0.62
    Gi
    0.62
    �
    0.61
    ilipp
    0.61
    Activations Density 0.018%

    No Known Activations