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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    không
    1.13
    hapi
    1.13
    de
    1.11
    ല്
    1.05
     หนังสือ
    1.01
    jeet
    1.00
     एनटीपीसी
    0.99
    ien
    0.96
    second
    0.96
     spok
    0.96
    POSITIVE LOGITS
    ு
    1.29
     rituals
    1.24
     atrocities
    1.22
     turtles
    1.21
    ря
    1.19
    <bos>
    1.18
     degrading
    1.17
     skulls
    1.17
     parasit
    1.17
     kneeling
    1.16
    Act Density 0.000%

    No Known Activations