© 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. 1677
    Prev
    Next
    INDEX
    Explanations

    repetitions of the phrase "Yes," usually followed by the emphasis on understanding or affirmation

    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
    zzle
    -0.82
    erk
    -0.71
    ams
    -0.69
    Hz
    -0.65
    acket
    -0.65
    vernment
    -0.64
    ulkan
    -0.63
    tyard
    -0.61
    Tube
    -0.61
    prise
    -0.61
    POSITIVE LOGITS
     chances
    0.76
    ends
    0.65
     intentions
    0.63
    ennes
    0.62
     intest
    0.62
     reflections
    0.62
     meanings
    0.61
     listeners
    0.59
     audiences
    0.58
     laughter
    0.58
    Activations Density 0.025%

    No Known Activations