© 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. 1429
    Prev
    Next
    INDEX
    Explanations

    words that express strong negative or absurd emotional reactions

    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
    ��
    -0.88
     rapport
    -0.71
     indisp
    -0.70
     reluct
    -0.69
    ANI
    -0.69
    anian
    -0.67
    regor
    -0.67
     Assist
    -0.66
    ドラゴン
    -0.66
     assistants
    -0.64
    POSITIVE LOGITS
    ushing
    0.80
    ious
    0.77
    ful
    0.76
    ening
    0.76
    acked
    0.75
    founded
    0.74
    iful
    0.70
    astic
    0.69
    actory
    0.69
    ulous
    0.68
    Activations Density 0.178%

    No Known Activations