© 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. 733
    Prev
    Next
    INDEX
    Explanations

    symbols or characters that likely represent formatting or encoding issues

    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
     leveled
    -0.76
     brand
    -0.68
     liner
    -0.66
     que
    -0.65
     shot
    -0.65
     candles
    -0.65
     jersey
    -0.65
     anthem
    -0.64
     liv
    -0.64
     Pradesh
    -0.64
    POSITIVE LOGITS
    Instead
    1.08
    Therefore
    1.06
    Refer
    1.05
    However
    1.05
    Specifically
    1.05
    During
    1.04
    When
    1.03
    He
    1.03
    Once
    1.03
    It
    1.03
    Activations Density 0.100%

    No Known Activations