© 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. 2862
    Prev
    Next
    INDEX
    Explanations

    phrases related to the creation of new items or entities

    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
    CLAIM
    -0.84
    actionDate
    -0.83
    DERR
    -0.83
    aucuses
    -0.83
    ーン
    -0.82
    ト
    -0.79
    Las
    -0.75
    ˜
    -0.74
    independence
    -0.74
    arth
    -0.73
    POSITIVE LOGITS
     ones
    1.02
    iated
    0.72
     arrivals
    0.71
     facts
    0.66
     Crimson
    0.66
     occasion
    0.66
     evenings
    0.65
     Nights
    0.64
     tone
    0.64
     outcomes
    0.64
    Activations Density 0.051%

    No Known Activations