INDEX
Explanations
cities/states
This neuron detects mentions of military stationing locations or base names.
New Auto-Interp
Negative Logits
monkeys
-0.07
Evans
-0.06
seekers
-0.06
(tool
-0.06
imperialism
-0.06
itous
-0.06
icine
-0.06
-default
-0.06
Maj
-0.06
(players
-0.06
POSITIVE LOGITS
Language
0.08
FormControl
0.07
commem
0.07
sik
0.06
قدر
0.06
Literal
0.06
----------- ↵
0.06
................
0.06
respuesta
0.06
Ri
0.06
Activations Density 0.007%