© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1354
    Prev
    Next
    INDEX
    Explanations

    the phrase "move on."

    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
    ordinate
    -0.70
    perse
    -0.68
    orus
    -0.65
     Stras
    -0.64
    arkin
    -0.63
    illard
    -0.61
    otte
    -0.61
    ector
    -0.60
     Osaka
    -0.60
     Cosmos
    -0.59
    POSITIVE LOGITS
     thereto
    0.70
    AUT
    0.69
    river
    0.66
     thereafter
    0.66
    LOCK
    0.66
    ibo
    0.66
    awaru
    0.65
    ••
    0.64
     VIDE
    0.64
    TA
    0.63
    Activations Density 0.035%

    No Known Activations