© 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. 707
    Prev
    Next
    INDEX
    Explanations

    references to Turkey and its geopolitical 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
     Sakuya
    -0.98
    デ
    -0.78
    ographers
    -0.72
    Nap
    -0.70
    Italy
    -0.68
     Bulgar
    -0.67
    hered
    -0.67
     Belarus
    -0.66
     Hindi
    -0.66
    anova
    -0.66
    POSITIVE LOGITS
    cheon
    0.67
    ks
    0.64
     slams
    0.63
    YN
    0.61
    nton
    0.59
     marquee
    0.59
    LEY
    0.56
     torches
    0.56
     credits
    0.54
     prompts
    0.54
    Activations Density 0.048%

    No Known Activations