© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 775
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negative trends or directions

    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
    uin
    -0.78
    rower
    -0.73
    ographs
    -0.69
    azon
    -0.67
    claim
    -0.63
    lic
    -0.63
    ylan
    -0.61
    Os
    -0.60
    starter
    -0.60
    ーン
    -0.59
    POSITIVE LOGITS
     direction
    0.80
     opposite
    0.79
    ffen
    0.66
     Spac
    0.62
     wrong
    0.62
     Direction
    0.62
     GT
    0.61
     vac
    0.61
     park
    0.61
     somebody
    0.60
    Activations Density 0.068%

    No Known Activations