© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2955
    Prev
    Next
    INDEX
    Explanations

    various forms of horizontal or vertical lines and symbols in the text

    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
    tics
    -0.75
    alian
    -0.74
    rael
    -0.73
    yr
    -0.68
    chens
    -0.68
    chen
    -0.66
    wright
    -0.66
    jad
    -0.64
    bane
    -0.63
     synerg
    -0.61
    POSITIVE LOGITS
    Reply
    0.84
    acea
    0.84
    WHERE
    0.75
    GAME
    0.73
    ��
    0.73
    QUIRE
    0.70
    fw
    0.70
    etheless
    0.68
    PDATE
    0.67
    CHAPTER
    0.66
    Activations Density 0.056%

    No Known Activations