© 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. 2506
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases associated with establishing or reinforcing something

    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
    20439
    -0.77
    dropping
    -0.73
    htaking
    -0.72
    Untitled
    -0.72
    liner
    -0.69
    ��
    -0.68
    ゴン
    -0.64
    idates
    -0.64
    ONS
    -0.64
    ONSORED
    -0.63
    POSITIVE LOGITS
     myths
    0.73
     consciousness
    0.69
     perceptions
    0.67
     orthodoxy
    0.67
     sanity
    0.66
     Binary
    0.65
    ibilities
    0.64
     notions
    0.64
    alties
    0.63
    ixie
    0.63
    Activations Density 0.238%

    No Known Activations