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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lɛ
    0.59
     Почему
    0.58
     Sedangkan
    0.56
     nást
    0.55
     Pourquoi
    0.53
     Misalnya
    0.53
     Seit
    0.53
     clé
    0.52
     Bagaimana
    0.52
     Why
    0.51
    POSITIVE LOGITS
    ↵↵
    0.58
    it
    0.57
    and
    0.51
    one
    0.51
    un
    0.50
    start
    0.49
    vert
    0.49
    all
    0.49
    as
    0.48
    optional
    0.48
    Act Density 0.000%

    No Known Activations