INDEX
Explanations
The neuron specifically fires on the “Plot” section heading in film articles.
New Auto-Interp
Negative Logits
Patio
-0.06
.x
-0.06
반
-0.06
ilater
-0.06
Barn
-0.06
跟
-0.06
congen
-0.06
handing
-0.06
hrá
-0.06
dataList
-0.06
POSITIVE LOGITS
idea
0.08
_Msk
0.07
misrepresented
0.06
ừa
0.06
-quote
0.06
rieved
0.06
_PM
0.06
IPO
0.06
rested
0.06
-development
0.06
Activations Density 0.007%