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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bak
    0.53
    isti
    0.49
    alie
    0.48
    ため
    0.48
     disple
    0.46
     interne
    0.45
     entertained
    0.45
    men
    0.44
    isted
    0.44
     Bak
    0.42
    POSITIVE LOGITS
    ﺠ
    0.52
    ﻘ
    0.52
    ﺶ
    0.50
     चुप
    0.50
     cuối
    0.48
    ﺪ
    0.48
    ﺸ
    0.46
     조금
    0.46
     ט
    0.45
    ꯣ
    0.45
    Act Density 0.000%

    No Known Activations