© 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. 1909
    Prev
    Next
    INDEX
    Explanations

    actions related to pouring and spreading in cooking

    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
     Duc
    -0.73
    istani
    -0.67
     tallest
    -0.58
    DN
    -0.57
    Lago
    -0.57
     cancell
    -0.57
    ⓘ
    -0.57
     unrestricted
    -0.57
     Springer
    -0.56
     hectares
    -0.56
    POSITIVE LOGITS
     batter
    0.77
    iqu
    0.71
    atio
    0.70
    illance
    0.64
    oice
    0.64
     ut
    0.64
    ixir
    0.63
    strument
    0.63
     somet
    0.63
    ibus
    0.61
    Activations Density 0.096%

    No Known Activations