© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 534
    Prev
    Next
    INDEX
    Explanations

    terms that indicate comparisons or limitations related to various contexts

    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
    kan
    -0.67
     fundament
    -0.61
     Kard
    -0.56
     Koch
    -0.54
     disadvant
    -0.54
    �
    -0.54
    redo
    -0.53
    975
    -0.52
    byter
    -0.52
    ��
    -0.52
    POSITIVE LOGITS
     thereto
    0.87
     to
    0.77
    bell
    0.68
    este
    0.67
    to
    0.67
    isol
    0.60
     isEnabled
    0.60
    ears
    0.58
    ertility
    0.57
    iola
    0.55
    Activations Density 1.223%

    No Known Activations