INDEX
Explanations
mentions of international diplomatic summits and agreements related to political and military actions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
752
+0.22
0.7%
50
+0.13
0.4%
453
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
752
+0.22
0.07
939
+0.13
0.06
1984
+0.10
0.06
Negative Logits
lmfao
-1.16
overcrow
-0.92
intersper
-0.91
upvoted
-0.91
<bos>
-0.91
😭😭
-0.90
hahah
-0.87
downvote
-0.81
shewn
-0.81
🥲
-0.80
POSITIVE LOGITS
Nö
0.99
solidar
0.98
vété
0.96
Lég
0.96
kram
0.94
Kategor
0.94
alkoh
0.93
ideolog
0.93
lele
0.93
reger
0.92
Activations Density 0.324%