INDEX
Explanations
mentions of electrical engineering concepts and terms
New Auto-Interp
Head Attr Weights
0:0.05
1:0.02
2:0.10
3:0.16
4:0.05
5:0.02
6:0.20
7:0.10
8:0.03
9:0.06
10:0.08
11:0.06
Negative Logits
asking
-1.12
mite
-1.10
cull
-1.10
iblings
-1.03
ibling
-1.01
stray
-0.94
hua
-0.92
inherit
-0.92
easing
-0.91
batches
-0.90
POSITIVE LOGITS
76561
1.20
ebus
1.20
ensable
1.19
cephal
1.18
ERA
1.18
riott
1.14
ivals
1.11
ASY
1.10
RED
1.09
uct
1.07
Activations Density 0.005%