INDEX
Explanations
instances of words and phrases that convey emotional struggles or conflicts
New Auto-Interp
Head Attr Weights
0:0.02
1:0.02
2:0.06
3:0.04
4:0.04
5:0.04
6:0.45
7:0.06
8:0.04
9:0.06
10:0.06
11:0.05
Negative Logits
++++
-1.30
VL
-1.27
��
-1.23
amy
-1.22
challeng
-1.21
osph
-1.20
MY
-1.18
ADRA
-1.18
unknown
-1.15
mast
-1.14
POSITIVE LOGITS
Celt
1.44
eers
1.25
enhagen
1.21
Geo
1.17
SpaceEngineers
1.16
Peb
1.16
ibly
1.15
Mineral
1.14
QC
1.14
Tile
1.13
Activations Density 0.004%