INDEX
Explanations
occurrences of the word "Sal" followed by a single digit
occurrences of the name "Sal" in various contexts
New Auto-Interp
Negative Logits
cc
-0.88
BUG
-0.78
tc
-0.74
XL
-0.73
pc
-0.71
gc
-0.71
pc
-0.70
DD
-0.69
plane
-0.69
Frame
-0.68
POSITIVE LOGITS
Sal
3.63
Sal
2.62
sal
2.14
sal
1.99
SAL
1.96
Salam
1.54
Salman
1.46
Salt
1.40
Sul
1.28
Chal
1.25
Activations Density 0.005%