INDEX
Explanations
references to coconut in various contexts
New Auto-Interp
Negative Logits
ilt
-0.17
ripp
-0.15
--------------------------------------------------------------------------↵
-0.15
itesse
-0.15
amba
-0.15
ForResult
-0.14
Mans
-0.14
Sor
-0.14
arshal
-0.13
zeug
-0.13
POSITIVE LOGITS
cid
0.15
iglia
0.15
omy
0.15
jured
0.14
cem
0.14
mey
0.14
ress
0.14
CHIP
0.14
sequences
0.14
ilde
0.14
Activations Density 0.002%