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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ā
    0.44
    Ah
    0.44
     Code
    0.44
     Time
    0.43
    ade
    0.43
    Wind
    0.42
    Hid
    0.41
     Medical
    0.41
    Life
    0.41
    ér
    0.40
    POSITIVE LOGITS
     testaceis
    0.51
     chieft
    0.49
     liquidated
    0.49
     postice
    0.48
    ं
    0.48
     seguenti
    0.48
     diciamo
    0.48
     tunique
    0.48
    ्रेसेस
    0.47
    ంక
    0.47
    Act Density 0.000%

    No Known Activations