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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Applied
    0.96
    性
    0.93
     Gesamt
    0.91
    ای
    0.88
    applied
    0.87
    pear
    0.86
    PR
    0.85
    C
    0.85
    Pl
    0.85
     tutti
    0.84
    POSITIVE LOGITS
     decrease
    1.18
     andDevice
    1.13
     heartbreaking
    1.09
     হইলেই
    1.04
     fancied
    1.04
     rejuvenating
    1.04
     slowdown
    1.02
     sobering
    1.01
     discomfort
    1.01
     boldness
    1.01
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.