INDEX
Explanations
references to the entity 'BT'
New Auto-Interp
Negative Logits
íĮħ
-0.18
erd
-0.16
ëįĺ
-0.16
ottle
-0.15
dirty
-0.15
nement
-0.14
esi
-0.14
uts
-0.14
asse
-0.13
ý
-0.13
POSITIVE LOGITS
thal
0.18
enor
0.16
BD
0.15
owo
0.15
ently
0.15
reck
0.15
oppins
0.15
ActionTypes
0.14
824
0.14
anca
0.14
Activations Density 0.014%