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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    u
    2.06
    و
    2.02
    ᴛ
    1.99
    𝙜
    1.96
    ر
    1.91
    ᴇ
    1.91
    ાઇ
    1.86
    ᴀ
    1.86
    acées
    1.83
    ાઈ
    1.83
    POSITIVE LOGITS
     quests
    1.94
    1.89
     harem
    1.81
    なかなか
    1.81
     Founders
    1.81
     Kyushu
    1.80
     BRAD
    1.79
    कर्ता
    1.78
     OpenAI
    1.78
     posit
    1.75
    Act Density 0.001%

    No Known Activations