© 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. 1389
    Prev
    Next
    INDEX
    Explanations

    quotation marks and signals of direct speech or citations

    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
     favourable
    -0.61
     shielded
    -0.60
     reckoning
    -0.58
     favorable
    -0.57
     periodic
    -0.56
     detailed
    -0.56
     stocking
    -0.54
     complying
    -0.53
     loyal
    -0.52
     resilient
    -0.51
    POSITIVE LOGITS
    Personally
    0.87
    Things
    0.80
    Honestly
    0.80
    Either
    0.80
    Perhaps
    0.80
    Unfortunately
    0.79
    Basically
    0.79
    Someone
    0.78
    Ultimately
    0.77
    Sometimes
    0.76
    Activations Density 0.069%

    No Known Activations