© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1000
    Prev
    Next
    INDEX
    Explanations

    phrases that signal questions or challenges, often accompanied by significant or definitive statements

    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
    redits
    -0.79
    ktop
    -0.75
    thood
    -0.75
    chedel
    -0.69
    pless
    -0.66
    yond
    -0.64
    dylib
    -0.63
    defined
    -0.63
    fram
    -0.63
    fusc
    -0.62
    POSITIVE LOGITS
     answer
    1.21
     problem
    0.86
     answers
    0.84
     gist
    0.81
    ory
    0.81
     reason
    0.77
     clue
    0.77
     solution
    0.77
     interesting
    0.75
     easiest
    0.75
    Activations Density 0.299%

    No Known Activations