© 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. 1927
    Prev
    Next
    INDEX
    Explanations

    punctuations or symbols that indicate significant events or changes

    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
    tnc
    -0.74
    ��
    -0.69
    rium
    -0.69
    ysis
    -0.67
     subsc
    -0.63
    kees
    -0.63
     Kahn
    -0.62
    ��
    -0.60
     playable
    -0.60
    fg
    -0.59
    POSITIVE LOGITS
    according
    0.84
     besides
    0.73
    force
    0.71
    forcing
    0.69
    together
    0.68
     according
    0.65
    iture
    0.64
    eland
    0.63
    without
    0.62
    asm
    0.62
    Activations Density 0.397%

    No Known Activations