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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ️
    1.84
     ktorí
    1.73
    انات
    1.72
    elf
    1.72
     esqu
    1.72
    єю
    1.71
     ocult
    1.69
     leia
    1.65
    siniz
    1.64
    dengan
    1.62
    POSITIVE LOGITS
    <bos>
    2.16
     hazelnuts
    2.06
    鎮
    2.00
    <0x0D>
    2.00
     cereals
    1.94
    Ꭲ
    1.90
     Monopoly
    1.87
     $%
    1.86
    friends
    1.85
    pronounced
    1.81
    Act Density 0.001%

    No Known Activations