INDEX
Explanations
instances of the verb "express" and its variations, indicating sentiment or opinions
New Auto-Interp
Negative Logits
_bm
-0.17
addCriterion
-0.17
èĽ
-0.16
iesz
-0.16
icipant
-0.15
sworth
-0.15
oulos
-0.14
ashboard
-0.14
enger
-0.14
adel
-0.14
POSITIVE LOGITS
072
0.16
rog
0.16
-proxy
0.15
dog
0.14
222
0.14
476
0.14
istant
0.14
223
0.14
416
0.14
711
0.14
Activations Density 0.004%