INDEX
Explanations
phrases related to duration and continuity
New Auto-Interp
Head Attr Weights
0:0.02
1:0.01
2:0.08
3:0.08
4:0.07
5:0.03
6:0.12
7:0.24
8:0.03
9:0.03
10:0.10
11:0.15
Negative Logits
Rasm
-1.35
unal
-1.33
picking
-1.32
iquette
-1.29
Translation
-1.27
idding
-1.25
Bonus
-1.22
osal
-1.19
Minor
-1.18
ixel
-1.17
POSITIVE LOGITS
agate
1.46
hement
1.33
discredited
1.25
hovah
1.24
adolescence
1.23
abstinence
1.22
incarcer
1.21
msec
1.21
stout
1.20
unsuccessful
1.19
Activations Density 0.009%