INDEX
Explanations
mentions or references to government entities or political discussions at the state level
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
849
+0.12
0.4%
67
+0.12
0.4%
1376
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
67
+0.12
0.06
849
+0.12
0.06
1376
+0.11
0.05
Negative Logits
MatIconModule
-0.56
velocityY
-0.55
bellissima
-0.46
(;;)
-0.45
neuri
-0.45
apellidos
-0.44
hoga
-0.44
articol
-0.42
geg
-0.41
bied
-0.41
POSITIVE LOGITS
state
1.15
state
1.14
State
1.09
State
1.05
STATE
1.03
STATE
1.01
getState
0.91
getState
0.90
states
0.90
states
0.88
Activations Density 0.140%