© 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. 1648
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Speaking" in 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
     arithmetic
    -0.64
     landsl
    -0.62
     brute
    -0.59
     denomin
    -0.58
     interven
    -0.58
     temptation
    -0.58
     inheritance
    -0.57
     intruder
    -0.57
     notor
    -0.57
     fingert
    -0.56
    POSITIVE LOGITS
    psc
    0.84
     exclusively
    0.74
    camp
    0.70
    arthed
    0.70
    CAST
    0.70
    atl
    0.66
     during
    0.65
     directly
    0.65
     anonymously
    0.64
     aloud
    0.64
    Activations Density 0.013%

    No Known Activations