© 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. 519
    Prev
    Next
    INDEX
    Explanations

    sentences that emphasize various points or arguments

    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
     miracle
    -0.63
     miraculous
    -0.62
     result
    -0.61
     remedy
    -0.61
     calam
    -0.59
     inexplicable
    -0.59
     awoken
    -0.59
     mitigating
    -0.59
     blinding
    -0.59
     discouraging
    -0.58
    POSITIVE LOGITS
     Firstly
    1.16
     Among
    0.96
    Firstly
    0.95
     One
    0.84
     Places
    0.81
    One
    0.80
     Publications
    0.77
     Articles
    0.75
     Some
    0.75
     Publication
    0.75
    Activations Density 0.329%

    No Known Activations