© 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. 1718
    Prev
    Next
    INDEX
    Explanations

    statements or opinions that reflect disapproval or critique

    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
     unle
    -0.74
     ded
    -0.73
     tips
    -0.71
     forged
    -0.71
     salute
    -0.70
     laud
    -0.69
     rewarded
    -0.68
     replen
    -0.68
     rede
    -0.68
     notices
    -0.67
    POSITIVE LOGITS
    umpy
    0.82
     Well
    0.71
     Whilst
    0.70
     Distance
    0.70
     Seems
    0.70
     Certainly
    0.69
    hey
    0.69
     Stability
    0.69
     Actor
    0.68
     Others
    0.68
    Activations Density 0.453%

    No Known Activations