INDEX
Explanations
phrases and words related to greetings and welcoming sentiments
greeting and welcome contexts
New Auto-Interp
Negative Logits
cheap
-0.38
Differentiation
-0.37
billig
-0.36
Cheap
-0.34
extra
-0.32
Defective
-0.32
Seung
-0.31
杭
-0.31
Jeho
-0.31
head
-0.31
POSITIVE LOGITS
featureID
0.69
WriteBarrier
0.66
للمعارف
0.63
Empfang
0.63
reception
0.62
greeted
0.62
greets
0.60
GOTREF
0.59
reception
0.58
greet
0.57
Activations Density 0.008%