INDEX
Explanations
connector phrases and transitional words that link ideas together
New Auto-Interp
Head Attr Weights
0:0.02
1:0.01
2:0.12
3:0.07
4:0.15
5:0.02
6:0.34
7:0.05
8:0.03
9:0.02
10:0.06
11:0.05
Negative Logits
ican
-1.48
��
-1.36
��
-1.28
Axis
-1.26
Registry
-1.24
Sax
-1.14
lite
-1.13
llan
-1.13
Indies
-1.12
ゴン
-1.10
POSITIVE LOGITS
AMY
1.28
ansky
1.22
NetMessage
1.21
ITH
1.18
exponential
1.16
eki
1.14
bullish
1.13
ETH
1.12
uberty
1.10
idious
1.10
Activations Density 0.079%