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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    aanse
    1.14
    arser
    1.12
    ní
    1.12
     esperamos
    1.12
    ताई
    1.12
    gegeben
    1.12
     zaw
    1.11
    玧
    1.10
    ae
    1.09
     materias
    1.09
    POSITIVE LOGITS
    NH
    1.03
    ложения
    1.00
    Speech
    0.99
    Dinner
    0.99
     intrinsically
    0.98
    ական
    0.97
    Safe
    0.96
    Gallery
    0.95
     carn
    0.95
     Dinner
    0.93
    Act Density 0.000%

    No Known Activations