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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    o
    1.32
    at
    1.09
    liminf
    1.08
    ه
    1.05
    чать
    1.03
    ির
    0.98
    вига
    0.95
    ט
    0.94
    divided
    0.94
    кси
    0.94
    POSITIVE LOGITS
     breach
    1.35
     actual
    1.32
     އެ
    1.32
    istic
    1.30
     Menteri
    1.24
    actual
    1.23
    ikka
    1.22
     shen
    1.20
     proceedings
    1.19
     Albanian
    1.18
    Act Density 0.000%

    No Known Activations