INDEX
Explanations
phrases related to control or monitoring in a context
New Auto-Interp
Negative Logits
lèvres
-0.69
datter
-0.65
Ibero
-0.65
ης
-0.64
Ayers
-0.62
BYTES
-0.61
graines
-0.61
WEEN
-0.61
Zhao
-0.61
Footprint
-0.60
POSITIVE LOGITS
CONTROL
1.44
control
1.44
Control
1.43
controls
1.40
Controls
1.36
control
1.33
Control
1.32
CONTROL
1.24
FormControl
1.22
Controlling
1.17
Activations Density 0.081%