INDEX
Explanations
ubuntu:latest or ubuntu:version
New Auto-Interp
Negative Logits
Later
0.52
kasnije
0.50
позже
0.49
later
0.47
später
0.47
späteren
0.45
později
0.45
Later
0.44
senere
0.44
később
0.43
POSITIVE LOGITS
jam
0.54
runners
0.54
runner
0.53
Jam
0.51
pat
0.50
Runner
0.47
focal
0.46
Runners
0.46
corred
0.46
Focal
0.46
Activations Density 0.001%