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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bachelor
    0.80
     oni
    0.77
     Bachelor
    0.76
     morte
    0.76
     Ба
    0.74
     vile
    0.74
     由
    0.73
     novels
    0.73
     Hilton
    0.72
     êtes
    0.72
    POSITIVE LOGITS
    chequer
    0.81
    融
    0.79
    Pclass
    0.71
    pls
    0.70
    cija
    0.68
     váll
    0.68
     Pferde
    0.68
    обс
    0.67
    ल्शियम
    0.67
    แอ
    0.67
    Act Density 0.000%

    No Known Activations