INDEX
Explanations
terms related to online communities, internet culture, and controversial online movements like '4chan' and 'Gamergate'
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
198
+0.17
0.5%
2006
+0.10
0.3%
20
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
198
+0.17
0.07
20
+0.10
0.05
2006
+0.10
0.05
Negative Logits
simpsons
-0.71
wikihow
-0.68
hasbro
-0.66
clayey
-0.66
funko
-0.65
snoopy
-0.64
imgur
-0.64
mlb
-0.63
ferru
-0.62
IFTT
-0.61
POSITIVE LOGITS
online
0.77
internet
0.66
online
0.65
internet
0.62
anonim
0.61
ciber
0.61
kram
0.61
poveznice
0.61
Internet
0.58
Internet
0.58
Activations Density 0.799%