© 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. 1678
    Prev
    Next
    INDEX
    Explanations

    instances of individuals expressing their emotions or opinions

    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
    ilk
    -0.82
    uscript
    -0.66
    CHA
    -0.64
    icle
    -0.63
    nesota
    -0.62
    aband
    -0.62
    acles
    -0.62
     collar
    -0.61
     spelling
    -0.61
     scaven
    -0.59
    POSITIVE LOGITS
     admiration
    1.28
     disgust
    1.26
     disapproval
    1.18
     displeasure
    1.17
     frustration
    1.12
     resentment
    1.10
     gratitude
    1.08
     disappointment
    1.07
     amaz
    1.06
     dislike
    1.05
    Activations Density 1.270%

    No Known Activations