© 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. 2446
    Prev
    Next
    INDEX
    Explanations

    commands or requests for repetition or continuation of actions

    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
    ilib
    -0.56
    rium
    -0.54
    iking
    -0.53
    odus
    -0.53
    isp
    -0.52
    osher
    -0.51
    isch
    -0.51
    �
    -0.50
    agger
    -0.50
    oxic
    -0.49
    POSITIVE LOGITS
    [/
    0.76
    ,...
    0.71
    ↵ 
    0.69
     Anyway
    0.69
    ¶
    0.69
     Reply
    0.68
    !!!!
    0.67
     solves
    0.66
     ********************************
    0.66
     :-)
    0.66
    Activations Density 1.122%

    No Known Activations