© 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. 991
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an error or problem occurrence

    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
     Euros
    -0.66
    zin
    -0.64
     tomorrow
    -0.63
     mac
    -0.61
     Samoa
    -0.61
    USD
    -0.60
     bye
    -0.60
     hun
    -0.60
     bigger
    -0.58
     scar
    -0.58
    POSITIVE LOGITS
     forbids
    0.69
    owers
    0.69
    ower
    0.68
    ");
    0.67
     [&
    0.65
    rants
    0.65
    ulsion
    0.65
     guiName
    0.63
     prohibits
    0.63
    ardless
    0.63
    Activations Density 0.009%

    No Known Activations