© 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. 1554
    Prev
    Next
    INDEX
    Explanations

    symbols or special characters that might indicate sentiment or emphasis

    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
     stock
    -0.67
     Mobil
    -0.61
     qualified
    -0.61
     sterling
    -0.58
     millenn
    -0.56
     Typh
    -0.56
    ividual
    -0.56
     descended
    -0.55
     Palestin
    -0.55
     shooter
    -0.55
    POSITIVE LOGITS
    furt
    0.84
    quickShipAvailable
    0.83
    Pause
    0.78
    particularly
    0.76
    especially
    0.76
    please
    0.74
    Therefore
    0.71
    write
    0.70
    felt
    0.69
    also
    0.69
    Activations Density 0.158%

    No Known Activations