INDEX
Explanations
This neuron activates on the second-person pronoun “you.”
New Auto-Interp
Negative Logits
ワ
-0.08
Sensor
-0.07
这样
-0.07
Mono
-0.07
M
-0.07
damit
-0.07
hbox
-0.06
Kurul
-0.06
Nep
-0.06
Causes
-0.06
POSITIVE LOGITS
intersection
0.07
queryString
0.06
lights
0.06
บาง
0.06
видов
0.06
routes
0.06
describe
0.06
kterou
0.06
=>
0.06
MODE
0.06
Activations Density 0.031%