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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1496
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the phrases "this" and "that" to indicate emphasis or reference in a discussion

    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
    ARE
    -0.76
    printed
    -0.74
    soDeliveryDate
    -0.72
    hops
    -0.68
    print
    -0.67
    interstitial
    -0.65
    enegger
    -0.65
    Lot
    -0.64
    soType
    -0.64
    Tokens
    -0.60
    POSITIVE LOGITS
    igating
    0.67
    oral
    0.67
    gat
    0.62
    igated
    0.60
     rud
    0.60
    uation
    0.60
     shrouded
    0.59
    aneous
    0.57
    �
    0.57
    olves
    0.57
    Activations Density 0.031%

    No Known Activations