© 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. 1090
    Prev
    Next
    INDEX
    Explanations

    phrases that initiate the idea of contemplation or consideration

    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
    pod
    -0.79
    kson
    -0.68
    zona
    -0.68
    ussion
    -0.68
    oub
    -0.67
    pton
    -0.67
    cephal
    -0.66
    gger
    -0.66
    thus
    -0.65
    assies
    -0.65
    POSITIVE LOGITS
     Ruin
    0.62
     Grind
    0.57
     therape
    0.57
     viz
    0.56
     chase
    0.56
     Annotations
    0.55
    awaru
    0.55
     torture
    0.55
     hunger
    0.55
     Grape
    0.54
    Activations Density 0.095%

    No Known Activations