INDEX
Explanations
politics, paranoia, passports, personal data, pipeline
New Auto-Interp
Negative Logits
𝙉
0.48
න්
0.47
ﺩ
0.42
a
0.41
٨
0.41
"')
0.39
hrt
0.39
kontakt
0.39
্লাস
0.38
touchstart
0.38
POSITIVE LOGITS
PZ
0.49
establishment
0.48
reorganization
0.48
politicians
0.46
PWM
0.46
piety
0.44
preoccupation
0.44
PSU
0.43
PSD
0.43
politics
0.42
Activations Density 0.797%