INDEX
Explanations
references to political events and figures
New Auto-Interp
Negative Logits
chan
-0.16
abox
-0.15
reso
-0.14
Äįan
-0.14
åħ³
-0.14
Tmp
-0.14
Anc
-0.14
BBC
-0.14
oppos
-0.14
Mechan
-0.14
POSITIVE LOGITS
TPM
0.18
progressive
0.18
operatives
0.17
GIF
0.16
Fusion
0.16
trackers
0.15
Blow
0.15
Brennan
0.15
OLA
0.15
-operative
0.15
Activations Density 0.164%