© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 908
    Prev
    Next
    INDEX
    Explanations

    instances of the word "perfectly."

    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
    udos
    -0.88
    OTOS
    -0.77
    aldi
    -0.75
    ados
    -0.74
    itely
    -0.74
    roups
    -0.69
    aze
    -0.65
    asus
    -0.65
     Cosmos
    -0.65
    ATCH
    -0.65
    POSITIVE LOGITS
     acceptable
    0.83
     manageable
    0.76
     calibrated
    0.69
    vention
    0.65
    gent
    0.65
     permissible
    0.65
    around
    0.64
    appropriate
    0.64
    haus
    0.63
     suitable
    0.62
    Activations Density 0.024%

    No Known Activations