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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝑎
    2.26
    ⎢
    2.15
    𝑏
    2.13
     unleashed
    2.13
    𝑑
    1.99
    𝑠
    1.97
     loosely
    1.95
    ্টি
    1.94
    ้
    1.93
    ीकरण
    1.91
    POSITIVE LOGITS
    ד
    2.01
    et
    2.00
    に
    1.89
    getting
    1.87
    ﻨ
    1.83
     distinguishing
    1.81
    giveness
    1.81
    色列
    1.80
    ට
    1.79
     joh
    1.79
    Act Density 0.000%

    No Known Activations