INDEX
Negative Logits
0.95
0.95
0.94
0.93
0.92
0.88
0.87
0.86
0.86
0.86
POSITIVE LOGITS
어서
0.69
java
0.66
IEnumerator
0.66
tourist
0.64
pesar
0.63
similar
0.61
unistd
0.61
podob
0.58
javax
0.57
recording
0.57
Activations Density 0.021%
어서
java
IEnumerator
tourist
pesar
similar
unistd
podob
javax
recording