© 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. 1975
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the act of careful selection or crafting

    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
    asus
    -0.70
     Cantor
    -0.68
    bia
    -0.65
    onds
    -0.65
     Victory
    -0.63
    onel
    -0.63
     Awakens
    -0.62
     Guilty
    -0.62
    aiden
    -0.61
    asta
    -0.60
    POSITIVE LOGITS
     curated
    0.91
     calibrated
    0.87
     crafted
    0.81
     tailored
    0.72
    utenberg
    0.72
     avoided
    0.69
     scripted
    0.68
     constructed
    0.67
     structured
    0.67
    crafted
    0.67
    Activations Density 0.054%

    No Known Activations