Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 102
    Prev
    Next
    INDEX
    Explanations

    the word "amid" and its variations, indicating contexts of simultaneous occurrences or conditions

    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
     Alloy
    -0.79
     AUTH
    -0.63
     Execution
    -0.62
     Ago
    -0.61
     Identified
    -0.59
    Allows
    -0.58
    oles
    -0.58
    MRI
    -0.57
     Ibid
    -0.56
     Pengu
    -0.56
    POSITIVE LOGITS
     escalating
    0.78
     rampant
    0.78
     raging
    0.77
     widespread
    0.77
     worsening
    0.72
    ecd
    0.72
     rising
    0.70
    س
    0.68
     complaints
    0.67
     constant
    0.67
    Activations Density 0.113%

    No Known Activations