© 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. 2768
    Prev
    Next
    INDEX
    Explanations

    instances of reasoning or justification across various contexts

    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
     corrid
    -0.66
    artz
    -0.59
     Kenn
    -0.57
     McCann
    -0.57
     Gins
    -0.56
    imus
    -0.56
     Ethiop
    -0.56
     RIS
    -0.56
     Ramirez
    -0.56
     Manziel
    -0.55
    POSITIVE LOGITS
    same
    1.08
     same
    0.93
    similar
    0.92
     similar
    0.88
     opposite
    0.85
    Same
    0.79
    actionDate
    0.79
     following
    0.77
    azes
    0.75
    asonable
    0.74
    Activations Density 1.113%

    No Known Activations