© 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. 1116
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Thus" indicating conclusions or transitions in argumentation

    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
    brew
    -0.83
    skinned
    -0.78
    ights
    -0.76
    Explore
    -0.74
    eds
    -0.74
    Downloadha
    -0.72
    oshenko
    -0.71
    depending
    -0.71
    Profile
    -0.71
    cream
    -0.71
    POSITIVE LOGITS
     expiration
    0.64
     distance
    0.64
     rumours
    0.63
     Livingston
    0.61
     anch
    0.61
     rumors
    0.61
     Gutierrez
    0.60
     Fi
    0.59
     Arcade
    0.59
     boundaries
    0.59
    Activations Density 0.052%

    No Known Activations