© 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. 492
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration or disapproval regarding actions or situations

    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
     neither
    -0.69
     whichever
    -0.69
     sourcing
    -0.65
     Flavoring
    -0.64
     testament
    -0.64
     ONLY
    -0.63
     NEVER
    -0.62
     irrespective
    -0.61
     notwithstanding
    -0.59
     nowhere
    -0.59
    POSITIVE LOGITS
    orthy
    0.77
    kered
    0.66
    mir
    0.64
     kinds
    0.63
    posure
    0.62
    ijah
    0.61
    bery
    0.61
    mosp
    0.60
    umer
    0.58
    ogg
    0.57
    Activations Density 1.354%

    No Known Activations