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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conflicts of interest

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Zem
    -0.54
    :+:
    -0.52
     General
    -0.50
     general
    -0.47
    WindowConstants
    -0.47
     Δ
    -0.46
    LEncoder
    -0.46
     Zap
    -0.45
    бно
    -0.45
     bào
    -0.45
    POSITIVE LOGITS
     الرخصة
    0.86
    Hauptartikel
    0.81
     Interests
    0.79
    UserScript
    0.75
     betweenstory
    0.72
     interests
    0.71
    interests
    0.70
     NDEBUG
    0.69
    Бележки
    0.69
     resourceCulture
    0.69
    Act Density 0.002%

    No Known Activations