INDEX
Explanations
foreign language literature
New Auto-Interp
Negative Logits
def
0.99
(
0.84
system
0.79
platform
0.77
overall
0.76
component
0.75
inline
0.74
correct
0.74
lack
0.73
key
0.73
POSITIVE LOGITS
estadounidense
1.47
aventuras
1.47
美國
1.45
personnages
1.43
américaine
1.40
poems
1.40
Amerikaanse
1.38
mitologia
1.37
romanzo
1.36
britannique
1.35
Activations Density 0.044%