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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ب
    0.49
     cuantos
    0.49
     habt
    0.48
     dividir
    0.44
     multiplicar
    0.44
     haben
    0.43
     dintre
    0.43
    هي
    0.42
     schle
    0.42
     degrades
    0.42
    POSITIVE LOGITS
     พ
    0.50
    daftar
    0.50
    tao
    0.49
    interpret
    0.48
     εξ
    0.46
    ፥
    0.45
    tai
    0.44
    AIRMAN
    0.44
    ją
    0.44
     유
    0.44
    Act Density 0.004%

    No Known Activations