INDEX
Explanations
terminology related to injections and related procedures
New Auto-Interp
Negative Logits
procedere
-0.63
VS
-0.49
z
-0.49
传
-0.48
ked
-0.48
mass
-0.47
next
-0.46
same
-0.46
vs
-0.45
spesso
-0.45
POSITIVE LOGITS
injection
1.25
Injection
1.21
inject
1.17
injected
1.12
itſelf
1.07
myſelf
1.05
injections
1.03
injecting
1.01
injection
0.99
Inject
0.96
Activations Density 0.082%