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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ял
    1.10
    然後
    1.08
    वा
    1.04
    ຫານ
    1.03
     DAL
    1.02
    я
    1.01
     ore
    1.01
     ores
    1.00
    βά
    0.99
    ı
    0.97
    POSITIVE LOGITS
    syn
    1.32
    Стро
    1.19
    showthread
    1.18
    te
    1.18
     уж
    1.15
    ことができる
    1.15
     unavoidable
    1.13
    tokenizer
    1.10
     transporter
    1.09
    theless
    1.08
    Act Density 0.000%

    No Known Activations