© 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. 1188
    Prev
    Next
    INDEX
    Explanations

    the repeated phrase "that" in various contexts

    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
    knit
    -0.78
    export
    -0.78
    iosyncr
    -0.77
    nesday
    -0.74
    dry
    -0.71
    ocry
    -0.70
    ozyg
    -0.69
    iasm
    -0.67
    igmatic
    -0.67
    phrine
    -0.67
    POSITIVE LOGITS
     humans
    0.71
     these
    0.63
     Jung
    0.57
     mortals
    0.56
     mobile
    0.56
     boundary
    0.55
     mercy
    0.55
    gans
    0.55
     computers
    0.55
     traps
    0.55
    Activations Density 0.174%

    No Known Activations