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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     kekerasan
    -0.83
     favorable
    -0.81
    rektur
    -0.79
     caratteri
    -0.79
    Fordítás
    -0.78
     adequate
    -0.75
    lider
    -0.74
     export
    -0.73
    favorable
    -0.73
     Cramer
    -0.73
    POSITIVE LOGITS
     Forumite
    1.20
    mathbb
    0.96
     moedas
    0.88
    밟
    0.85
     sofa
    0.82
    Crédit
    0.82
     Produtos
    0.82
    FRAGMENT
    0.79
     фору
    0.79
     nocturn
    0.79
    Act Density 0.003%

    No Known Activations