INDEX
Explanations
instances where the text prompts further reading or clicking for more information
New Auto-Interp
Negative Logits
UIBar
-0.14
Fut
-0.14
neg
-0.14
PWD
-0.14
aea
-0.14
hoe
-0.14
ary
-0.14
HEME
-0.13
aby
-0.13
Crafting
-0.13
POSITIVE LOGITS
jump
0.26
Continue
0.25
Continue
0.25
Read
0.24
read
0.23
Read
0.23
read
0.23
continue
0.23
continue
0.22
READ
0.20
Activations Density 0.069%