INDEX
Explanations
references to the character Judas in various contexts
New Auto-Interp
Negative Logits
orts
-0.17
etics
-0.17
ebo
-0.16
ections
-0.16
adian
-0.16
classname
-0.15
orting
-0.15
.sponge
-0.15
adians
-0.15
à¹Ģà¸ķà¸Ńร
-0.15
POSITIVE LOGITS
gement
0.29
gment
0.28
icial
0.28
gments
0.27
ging
0.26
icious
0.26
gements
0.26
ith
0.25
iciary
0.24
icator
0.23
Activations Density 0.011%