© 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. 2580
    Prev
    Next
    INDEX
    Explanations

    numerical statistics or scores in a sports context

    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
    undo
    -0.81
    �
    -0.70
    Chance
    -0.69
    inker
    -0.68
     Bram
    -0.67
    zman
    -0.66
    zer
    -0.65
    xton
    -0.64
    utter
    -0.64
    byter
    -0.64
    POSITIVE LOGITS
    obil
    0.78
     milit
    0.78
     countryside
    0.76
    emort
    0.72
    yss
    0.72
     Flavoring
    0.69
     woods
    0.68
     recruits
    0.67
    iants
    0.65
    bernatorial
    0.65
    Activations Density 0.026%

    No Known Activations