INDEX
Explanations
connections between individuals and their achievements
New Auto-Interp
Negative Logits
atak
-0.17
AIT
-0.15
Podesta
-0.15
quina
-0.14
iag
-0.14
åį·
-0.14
IRECT
-0.14
igham
-0.14
Torch
-0.14
ÑĪов
-0.14
POSITIVE LOGITS
Pi
0.26
Aad
0.26
Ton
0.25
Bram
0.25
Ferry
0.24
Lies
0.24
Harm
0.24
Jan
0.24
Fem
0.24
Taco
0.23
Activations Density 0.012%