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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     truth
    0.72
    truth
    0.65
    í
    0.64
     Truth
    0.63
     ban
    0.62
     čern
    0.62
     core
    0.62
     truths
    0.61
    0.60
     decad
    0.60
    POSITIVE LOGITS
    <unused849>
    0.83
    <unused802>
    0.81
     impatience
    0.80
    पचारिक
    0.80
    otiti
    0.77
    <unused945>
    0.77
    <unused1781>
    0.77
     spontaneity
    0.76
    <unused971>
    0.76
    aditional
    0.76
    Act Density 2.487%

    No Known Activations