INDEX
Explanations
scientific/experimental setups
The neuron activates on verbs describing medical examination or treatment procedures.
New Auto-Interp
Negative Logits
Zoe
-0.07
Licensed
-0.06
achievement
-0.06
sled
-0.06
obesity
-0.06
lots
-0.06
agents
-0.06
殊
-0.06
vhodné
-0.06
.authService
-0.06
POSITIVE LOGITS
?’
0.07
greeted
0.06
?”
0.06
embre
0.06
ENOMEM
0.06
тия
0.06
\Event
0.06
Ў
0.06
],'
0.06
jug
0.06
Activations Density 0.025%