© 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. 751
    Prev
    Next
    INDEX
    Explanations

    character names or terms with accents in their spelling

    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
    Compar
    -0.73
     Compan
    -0.67
     Ba
    -0.66
    Animation
    -0.64
     Sacrament
    -0.64
     Romeo
    -0.64
    ه
    -0.61
     Instrument
    -0.61
     aux
    -0.59
     Malone
    -0.59
    POSITIVE LOGITS
    redd
    0.92
    mouth
    0.75
    odder
    0.71
    ocket
    0.70
    athom
    0.70
    peak
    0.69
    awar
    0.68
    dim
    0.67
    idges
    0.66
    NG
    0.66
    Activations Density 0.065%

    No Known Activations