INDEX
Explanations
action verbs after 'for' or 'to'
New Auto-Interp
Negative Logits
unei
0.50
μιας
0.45
einer
0.45
într
0.44
một
0.44
beginnen
0.41
Een
0.41
prosegu
0.41
isang
0.40
एक
0.40
POSITIVE LOGITS
detecting
0.48
бора
0.48
discovering
0.46
获取
0.46
evaluating
0.46
Если
0.45
Detect
0.44
detect
0.43
发现
0.42
getAll
0.42
Activations Density 0.103%