© 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. 457
    Prev
    Next
    INDEX
    Explanations

    references to news media outlets

    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
    chell
    -0.78
    uve
    -0.65
    ouf
    -0.64
     Buckley
    -0.63
    iod
    -0.63
    jri
    -0.62
    sen
    -0.61
     Citiz
    -0.61
    bern
    -0.60
     Stephens
    -0.60
    POSITIVE LOGITS
    utics
    0.70
    atts
    0.67
    letters
    0.62
    efeated
    0.62
    activated
    0.59
    amous
    0.58
    utical
    0.58
    onential
    0.57
    pees
    0.56
    VERTISEMENT
    0.56
    Activations Density 0.078%

    No Known Activations