INDEX
Explanations
phrases related to free speech
references to free speech and related legal concepts
New Auto-Interp
Negative Logits
BALL
-0.76
Stab
-0.75
Pes
-0.70
Maz
-0.67
Mirage
-0.66
hews
-0.66
ellen
-0.65
laus
-0.65
ENA
-0.63
Shore
-0.63
POSITIVE LOGITS
speech
1.01
rights
1.01
rights
0.94
Rights
0.82
liberties
0.79
protections
0.79
speech
0.78
ible
0.76
freedoms
0.75
edom
0.75
Activations Density 0.051%