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

    Neuronpedia

    INDEX
    Explanations

    phrases related to guidelines or recommendations

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

    recommendations for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Хьажоргаш
    -0.45
    WebServlet
    -0.39
     maș
    -0.37
    Inside
    -0.36
    Computers
    -0.35
     dieux
    -0.35
     Signalez
    -0.34
    有一种
    -0.34
     fédé
    -0.33
     Juifs
    -0.33
    POSITIVE LOGITS
     recommendations
    1.98
     Recommendations
    1.84
    Recommendations
    1.72
    recommendations
    1.63
     recommendation
    1.58
     Recommendation
    1.50
     RECOMMENDATIONS
    1.47
    RECOMMENDATIONS
    1.43
    Recommendation
    1.43
    recommendation
    1.30
    Act Density 0.004%

    No Known Activations