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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    use
    0.92
    a
    0.89
    ی
    0.89
    و
    0.88
    وية
    0.75
    ה
    0.74
    容易
    0.70
    лни
    0.69
    il
    0.68
    lung
    0.68
    POSITIVE LOGITS
     Leinster
    0.96
    ্স্ট
    0.96
    ым
    0.88
     invertible
    0.86
     डीएल
    0.86
     Jackman
    0.86
    𝒅
    0.85
     HubSpot
    0.84
    れます
    0.84
     OnePlus
    0.84
    Act Density 0.001%

    No Known Activations