© 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. 1684
    Prev
    Next
    INDEX
    Explanations

    the phrase "free and open" along with variations of "to."

    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
    olson
    -0.76
    imes
    -0.72
     Nanto
    -0.70
    ieth
    -0.67
    baugh
    -0.67
    ucci
    -0.63
    soDeliveryDate
    -0.63
    hya
    -0.62
     preached
    -0.62
    iceps
    -0.62
    POSITIVE LOGITS
    blind
    0.68
     principled
    0.66
     bip
    0.65
    Independent
    0.64
    adult
    0.63
    :(
    0.62
     priv
    0.62
     blind
    0.62
     independent
    0.61
     impartial
    0.61
    Activations Density 0.034%

    No Known Activations