INDEX
Explanations
scalable
This neuron activates on mentions of a system’s “scalable” characteristic.
New Auto-Interp
Negative Logits
pools
-0.07
jugar
-0.07
.djang
-0.07
reproduce
-0.07
りと
-0.06
умов
-0.06
oste
-0.06
Thomas
-0.06
cortical
-0.06
Diese
-0.06
POSITIVE LOGITS
scalable
0.09
-ready
0.07
estad
0.07
scalability
0.07
millennials
0.07
at
0.07
calam
0.07
extr
0.07
Lester
0.06
GIT
0.06
Activations Density 0.008%