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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     alike
    0.67
     singing
    0.65
     calibre
    0.65
     ong
    0.64
     accelerating
    0.64
     movies
    0.64
     starring
    0.64
     modulo
    0.64
     od
    0.63
     crashing
    0.61
    POSITIVE LOGITS
    Issued
    0.63
     والذي
    0.58
     இந்நிலையில்
    0.58
     котором
    0.55
     эту
    0.54
     तौर
    0.52
    bio
    0.52
    которы
    0.52
    แค่
    0.52
    Этот
    0.52
    Act Density 0.114%

    No Known Activations