© 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. 2025
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases emphasizing the phrase "might as well."

    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
     ensued
    -0.76
     arises
    -0.71
    ��
    -0.68
     Bene
    -0.68
     existed
    -0.67
    ��
    -0.67
    Choice
    -0.66
    existent
    -0.66
    quished
    -0.65
    aimon
    -0.65
    POSITIVE LOGITS
     wear
    0.85
     swing
    0.79
    hang
    0.78
     slip
    0.76
     die
    0.74
    inth
    0.73
    stall
    0.72
     stall
    0.71
     bleed
    0.69
     finish
    0.68
    Activations Density 0.186%

    No Known Activations