Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to reports and recommendations related to policy and regulatory tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "recommendations" or similar terms

    np_acts-logits-general · gemini-2.0-flash

    recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.56
     switching
    -0.51
    izers
    -0.51
     Switching
    -0.50
    pruch
    -0.50
    cury
    -0.50
    switching
    -0.49
    lesia
    -0.49
     ostavi
    -0.49
    obic
    -0.49
    POSITIVE LOGITS
     recommendations
    2.11
     recommendation
    1.81
     Recommendations
    1.79
    Recommendations
    1.70
    recommendations
    1.66
     Recommendation
    1.57
     RECOMMENDATIONS
    1.56
     recommend
    1.52
     recommending
    1.51
     recommandations
    1.49
    Act Density 0.411%

    No Known Activations