© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 892
    Prev
    Next
    INDEX
    Explanations

    technical references related to software modules and configurations

    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
     Shutterstock
    -0.77
     GOODMAN
    -0.67
     ideally
    -0.65
    imar
    -0.65
     Creator
    -0.65
    nesday
    -0.63
     envis
    -0.63
     guiName
    -0.63
     foreseeable
    -0.63
    uably
    -0.62
    POSITIVE LOGITS
     ${
    0.64
    ${
    0.63
    `
    0.61
    DEBUG
    0.61
    guard
    0.61
     piety
    0.61
    OH
    0.60
    issy
    0.60
    iced
    0.60
    ({
    0.58
    Activations Density 0.060%

    No Known Activations