© 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. 2267
    Prev
    Next
    INDEX
    Explanations

    statements or conclusions that begin with "This" indicating the significance or impact of previous content

    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
    rollers
    -0.78
    aths
    -0.70
     Shots
    -0.69
    olicy
    -0.69
    ucky
    -0.66
     Airl
    -0.65
    irlf
    -0.65
    ittees
    -0.64
    ricks
    -0.63
    dinand
    -0.63
    POSITIVE LOGITS
     suggests
    0.98
     indicates
    0.96
     reinforces
    0.96
     implies
    0.94
     includes
    0.93
     requires
    0.93
     encourages
    0.92
     violates
    0.91
     contradicts
    0.91
     demonstrates
    0.89
    Activations Density 0.084%

    No Known Activations