INDEX
Explanations
phrases related to locations or movement into a particular place
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1482
+0.13
0.5%
1023
+0.13
0.5%
228
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1334
+0.13
0.06
161
+0.13
0.05
1023
+0.12
0.05
Negative Logits
Bardzo
-0.48
pecuni
-0.46
Referencoj
-0.46
irlo
-0.44
Cantidad
-0.41
emplea
-0.41
sioni
-0.41
envía
-0.40
actúa
-0.40
Mostrar
-0.40
POSITIVE LOGITS
INTO
1.09
Into
1.07
Into
1.01
into
0.97
into
0.97
INTO
0.94
onto
0.62
olkata
0.55
fjspx
0.54
hunde
0.54
Activations Density 0.138%