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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     scanning
    0.46
    נון
    0.46
    ۹
    0.44
     »,
    0.42
    ಸ್ತ
    0.42
     »
    0.41
    ۸
    0.40
    ﻡ
    0.40
    ﺹ
    0.40
    큼
    0.40
    POSITIVE LOGITS
     이야
    0.48
     машиналары
    0.47
     полного
    0.46
     चाहते
    0.45
     избежать
    0.45
    ikia
    0.44
     त्यांना
    0.43
     কথায়
    0.43
    朋友們
    0.43
     जिसके
    0.42
    Act Density 0.004%

    No Known Activations