INDEX
Explanations
descriptions of ancient texts, literature, and historical artifacts
references to historical texts and literary works
New Auto-Interp
Negative Logits
isode
-0.85
IDA
-0.84
iott
-0.79
blockers
-0.78
interns
-0.77
GamerGate
-0.76
cipled
-0.76
Comcast
-0.76
Zucker
-0.74
Plug
-0.71
POSITIVE LOGITS
traditions
1.04
Zoro
1.01
funer
0.98
inscription
0.94
araoh
0.94
inscribed
0.92
compositions
0.92
motif
0.90
Egyptians
0.89
Ottoman
0.89
Activations Density 0.319%