© 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. 501
    Prev
    Next
    INDEX
    Explanations

    the past tense of the verb "to do."

    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
    icle
    -0.88
    ICLE
    -0.71
    IDER
    -0.69
     Cue
    -0.66
     Squirrel
    -0.64
     Deadpool
    -0.64
    cart
    -0.64
     Eisen
    -0.62
     Coul
    -0.61
     Orange
    -0.61
    POSITIVE LOGITS
     recommend
    0.72
    otiation
    0.69
     never
    0.69
     advise
    0.68
    get
    0.68
    ths
    0.67
    lia
    0.66
    never
    0.66
    ugh
    0.66
     happily
    0.65
    Activations Density 0.014%

    No Known Activations