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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1446
    Prev
    Next
    INDEX
    Explanations

    the word "but" and its variations indicating contrast or opposition in statements

    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
     uncond
    -0.68
    umo
    -0.68
    SpaceEngineers
    -0.64
     necessarily
    -0.64
    worth
    -0.62
     irrespective
    -0.62
    esting
    -0.62
    emp
    -0.61
    NAS
    -0.61
    ��
    -0.61
    POSITIVE LOGITS
    rote
    0.61
     brace
    0.55
     jams
    0.54
     proble
    0.52
    rians
    0.52
    Balance
    0.51
     expects
    0.51
     Hungry
    0.51
    LED
    0.51
    RANT
    0.50
    Activations Density 0.129%

    No Known Activations