© 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. 1669
    Prev
    Next
    INDEX
    Explanations

    terms related to substitutions and replacements in roles or positions

    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
    tiny
    -0.69
     probability
    -0.68
    grounds
    -0.65
     calibration
    -0.64
     helicop
    -0.61
     ECB
    -0.61
     probabilities
    -0.61
    intelligence
    -0.60
     medically
    -0.60
     lawy
    -0.60
    POSITIVE LOGITS
     Alexis
    0.91
     Jamal
    0.91
     Kurt
    0.89
     Cla
    0.86
     Quentin
    0.86
     Byron
    0.85
     Jared
    0.85
     Elijah
    0.84
     Anthony
    0.84
     Dennis
    0.83
    Activations Density 0.178%

    No Known Activations