INDEX
Explanations
references to LGBTQ topics and experiences, specifically focusing on the term "gay" and related concepts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1984
+0.12
0.4%
325
+0.12
0.4%
1763
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
325
+0.12
0.04
1763
+0.12
0.03
1443
+0.11
0.03
Negative Logits
ToScroll
-0.54
ImageContext
-0.54
Itoa
-0.54
Viitteet
-0.54
núm
-0.53
ManagedBean
-0.53
intios
-0.53
guma
-0.51
ITIS
-0.50
LocationManager
-0.50
POSITIVE LOGITS
gay
1.30
Gay
1.17
gay
1.15
Gay
1.13
homosexual
1.12
GAY
1.08
gays
1.07
homosexuality
0.92
LGBT
0.90
lesbian
0.87
Activations Density 0.049%