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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ই
    1.41
    िंग
    1.28
     única
    1.28
     altra
    1.27
    ﻲ
    1.27
    ﺔ
    1.25
    되는
    1.23
     처음
    1.21
    د
    1.20
    만
    1.20
    POSITIVE LOGITS
     propensity
    1.20
    Sprintf
    1.18
    lays
    1.12
    жа
    1.10
     rằng
    1.09
     wasteland
    1.06
    waffe
    1.05
     pathways
    1.05
    便是
    1.05
    ushed
    1.02
    Act Density 0.033%

    No Known Activations