INDEX
Explanations
references to historical figures and their relationships
New Auto-Interp
Negative Logits
zug
-0.15
.sponge
-0.15
zc
-0.15
TZ
-0.14
numeric
-0.14
@dynamic
-0.14
ldb
-0.14
ulings
-0.14
,{"-0.14
"**
-0.14
POSITIVE LOGITS
‘
0.20
alien
0.18
licence
0.18
temp
0.18
alias
0.18
alias
0.17
Alice
0.16
temp
0.16
chan
0.16
fe
0.15
Activations Density 0.005%