© 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. 2386
    Prev
    Next
    INDEX
    Explanations

    conditional statements or phrases indicating intent or possibility

    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
    ゴ
    -0.69
    ONSORED
    -0.68
    hered
    -0.62
     weeping
    -0.61
    76561
    -0.60
     Peb
    -0.59
    ciating
    -0.59
     Betty
    -0.59
    blem
    -0.58
     scrambling
    -0.58
    POSITIVE LOGITS
     settle
    0.80
     escalate
    0.79
     migrate
    0.77
     continue
    0.77
     Improve
    0.75
     intensify
    0.74
     apply
    0.74
    ocate
    0.72
     solve
    0.72
     compensate
    0.72
    Activations Density 0.117%

    No Known Activations