INDEX
Explanations
This neuron detects occurrences of the phrase “Spring Boot.”
New Auto-Interp
Negative Logits
(details
-0.07
Monad
-0.07
smell
-0.06
.gray
-0.06
إن
-0.06
örg
-0.06
cích
-0.06
Team
-0.06
Monad
-0.06
staffers
-0.06
POSITIVE LOGITS
uitar
0.07
QE
0.06
(;
0.06
-boot
0.06
Toolkit
0.06
ूर
0.06
acha
0.06
ngôi
0.06
PPC
0.06
Στα
0.06
Activations Density 0.002%